PulseAugur
EN
LIVE 10:49:50
ENTITY Gemma 2-2B

Gemma 2-2B

PulseAugur coverage of Gemma 2-2B — every cluster mentioning Gemma 2-2B across labs, papers, and developer communities, ranked by signal.

Show in brief
Total · 30d
7
25 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
6
21 over 90d
TIER MIX · 90D
TOPICS
RELATIONSHIPS
SENTIMENT · 30D

6 day(s) with sentiment data

RECENT · PAGE 1/2 · 25 TOTAL
  1. TOOL · CL_196113 ·

    New method uses Koopman operator for model interpretability

    Researchers have developed a new method for mechanistic interpretability called "Intrinsic Structure" that uses the Koopman operator to analyze the spectral properties of a model's internal dynamics. This approach aims …

  2. TOOL · CL_195168 ·

    HyperSAE uses Poincaré geometry to boost Sparse Autoencoder performance

    A new PyTorch library called HyperSAE has been developed to improve the efficiency of Sparse Autoencoders (SAEs) by employing Poincaré hyperbolic geometry. This approach addresses the limitations of standard SAEs, which…

  3. TOOL · CL_193516 ·

    New LLM fine-tuning method targets performance and carbon emission break-even

    Researchers have developed a new fine-tuning method that incorporates a differentiable energy surrogate to optimize for both performance and carbon emissions in Large Language Models (LLMs). This approach aims to achiev…

  4. TOOL · CL_191133 ·

    New Tiled SVD Method Extracts Network Mechanisms Directly From Weights

    Researchers have developed a new method called column-tiled SVD to extract usable weight mechanisms directly from linear sites within neural networks. This approach identifies concepts within the network's weights thems…

  5. TOOL · CL_165006 ·

    New training method enhances LLM interpretability by reducing signal loss

    Researchers have developed a new method called replacement-aware training to improve the interpretability of large language models. This technique trains sparse auto-encoders (SAEs) to be robust to errors introduced by …

  6. TOOL · CL_160861 ·

    Gemma 2-2B research finds active feature planes have less holonomy

    A new research paper published on arXiv investigates the concentration of holonomy within specific feature planes of the Gemma 2-2B model. The study preregistered its methodology and analysis rules before inspecting the…

  7. TOOL · CL_151945 ·

    New 'prolepsis' phenomenon identified in small transformer models

    Researchers have identified a phenomenon called 'prolepsis' in small transformer models, where the model commits to a decision early in its processing and cannot correct it. This commitment is sustained by task-specific…

  8. SIGNIFICANT · CL_100834 ·

    Google's Gemma 2 models achieve high performance with efficient architecture

    Google's new Gemma 2 models, particularly the 27B parameter version, are demonstrating significant performance gains through architectural innovations rather than just increased size. These models utilize a hybrid atten…

  9. RESEARCH · CL_99632 ·

    New research identifies actionable directions to mitigate AI model misalignment

    Researchers have identified a method to detect and mitigate emergent misalignment in language models by analyzing activation directions. This approach, tested across four model families including Qwen2.5-1.5B, Gemma-2-2…

  10. TOOL · CL_91442 ·

    New method improves neural network interpretability by addressing dense activations

    Researchers have proposed a new method to improve the interpretability of neural networks by questioning the assumption that all activation content can be sparsely decomposed. They hypothesize that activations contain a…

  11. TOOL · CL_89542 ·

    Specialized AI judge fails to cut audit costs, offers limited help

    A researcher explored using a lightweight, specialized judge model (Gemma 2-2B) to assist AI agents in identifying misalignment within audits. While the judge was consistently used by the agents, it only proved helpful …

  12. TOOL · CL_75523 ·

    Transformer residual streams show geometry of time, concentrate context

    Researchers have discovered that the residual stream in transformers, often likened to working memory, exhibits a distinct geometry related to time. By analyzing the Gemma-2-2B model, they found that information persist…

  13. TOOL · CL_58973 ·

    LLM Vulnerability Detection Relies on Safety Patterns, Not Direct Signatures

    Researchers have employed mechanistic interpretability to analyze how Large Language Models (LLMs) detect software vulnerabilities, focusing on the Gemma-2-2b model. Their study revealed that the model primarily identif…

  14. TOOL · CL_56474 ·

    Decision Trees Enhance LLMs for Molecular Property Prediction

    Researchers have developed a new method called TreeKD to improve the accuracy of large language models (LLMs) in molecular property prediction, a crucial task in drug discovery. TreeKD works by distilling knowledge from…

  15. TOOL · CL_56280 ·

    AI models detect PCOS, eating disorders with explainability

    Researchers have developed open-source language models to detect a triple burden of polycystic ovary syndrome (PCOS), body image distress, and disordered eating in social media posts. Using a dataset of 1,000 PCOS-relat…

  16. TOOL · CL_51447 ·

    New FiPS framework compresses transformer models with minimal accuracy loss

    Researchers have developed a new framework called Fine-grained Parameter Sharing (FiPS) to compress large transformer models. FiPS combines cross-block parameter sharing, low-rank factorization, and sparsity within a si…

  17. TOOL · CL_51194 ·

    New protocol detects LLM provider model substitutions

    A new research paper proposes a commit-open protocol to detect when hosted large language model providers substitute cheaper models for advertised ones. The protocol uses Merkle trees to commit to sparse autoencoder (SA…

  18. RESEARCH · CL_44009 ·

    LLM analysis method reveals training data secrets and ethical risks

    Researchers have developed a method using singular value decomposition (SVD) of a large language model's weight matrix to reveal interpretable semantic subspaces. This technique, requiring minimal code and no model infe…

  19. TOOL · CL_15954 ·

    CorrSteer method enhances LLM steering using correlated sparse autoencoder features

    Researchers have developed CorrSteer, a novel method for steering large language models (LLMs) during generation using features extracted from Sparse Autoencoders (SAEs). This technique correlates sample correctness wit…

  20. RESEARCH · CL_10249 ·

    DB-KSVD algorithm offers scalable approach to disentangling high-dimensional embedding spaces

    Researchers have introduced DB-KSVD, a novel dictionary learning algorithm designed to disentangle high-dimensional embedding spaces in large transformer models. This method adapts the classic KSVD algorithm to scale ef…