Gemma 2
PulseAugur coverage of Gemma 2 — every cluster mentioning Gemma 2 across labs, papers, and developer communities, ranked by signal.
- 2026-09-02 product_launch Google released Gemma 2, a new family of open models with improved architectural efficiency. source
- 2026-07-22 product_launch Google has released Gemma 2, a new generation of its open-source AI models, available in 9B and 27B parameter sizes. source
- 2026-07-17 product_launch Google updated its Gemma 2 model family, improving prompt processing speeds. source
- 2026-07-08 product_launch Google has released Gemma 2, a new family of open large language models in 9B and 27B parameter sizes. source
- 2026-06-19 product_launch Google released its new Gemma 2 family of AI models, emphasizing architectural efficiency for improved performance. source
4 day(s) with sentiment data
-
LLM judges show family bias in preference evaluations, study finds
A new arXiv paper investigates how the choice of Large Language Model (LLM) used for judging affects preference outcomes in pairwise comparisons. The study found that the LLM judge's own model family significantly influ…
-
New TEFM framework boosts LLM efficiency and faithfulness for structured data
Researchers have introduced TEFM (Token-Efficient Faithful Modeling), a new framework designed to improve the application of large language models (LLMs) to structured data analysis in critical domains. TEFM addresses t…
-
Gemma 2 and 3 translation features show limited cross-lingual transfer
A new research paper investigates the cross-lingual validity of Sparse Autoencoder (SAE) features in Google's Gemma 2 and Gemma 3 language models. The study found that while many features appear frequently across differ…
-
Google releases Gemma 2 with efficient architecture, outperforming larger models
Google has released Gemma 2, featuring new 9B and 27B parameter models that prioritize architectural efficiency over sheer size. These models utilize a redesigned transformer architecture with a hybrid attention mechani…
-
New QDRT framework generates diverse and effective LLM attack prompts
Researchers have introduced Quality-Diversity Red-Teaming (QDRT), a novel framework designed to enhance the safety and robustness of large language models (LLMs). QDRT addresses limitations in existing red-teaming metho…
-
Google releases PaliGemma vision models for fine-tuning
Google has released the PaliGemma model family, which are open-source vision-language models designed for fine-tuning rather than general chatbot use. These models combine Google's SigLIP vision encoder with Gemma langu…
-
Google releases Gemma 2 open models, challenging larger proprietary systems
Google has launched Gemma 2, a new generation of its open-source AI models, featuring redesigned architectures and improved efficiency. The 27-billion parameter version offers performance comparable to models twice its …
-
Google secretly updates Gemma 2 models, drawing researcher criticism
Google has quietly updated its Gemma 2 model family, improving prompt processing speeds by up to 70%. This performance enhancement, however, has drawn criticism from researchers due to the lack of a version name change,…
-
New J-Space Protocol Assesses AI Model Safety Internally
Researchers have introduced JADR, a new protocol for evaluating the internal safety mechanisms of AI models. This method analyzes a model's Jacobian space (J-space) before response generation, offering a more direct ass…
-
Google releases Gemma 2 open LLM family with efficiency-focused architecture
Google has released Gemma 2, an updated family of open large language models available in 9B and 27B parameter sizes. These models incorporate significant architectural changes, including a hybrid attention mechanism an…
-
New method reveals shared algorithmic cores in large language models
Researchers have developed a new method called Algorithmic Core Extraction (ACE) to identify the essential computational structures within transformer models. This technique isolates compact subspaces that are crucial f…
-
LLM dialogue agents improve safety with new prompting strategy · 2 sources tracked
A new research paper explores a lightweight prompting strategy to improve the safety of large language models in task-oriented dialogue when database interactions fail. The proposed "Guided-Retry" method aims to reduce …
-
Language models' "evaluation awareness" shifts with scale, study finds
A new research paper explores how open-weight language models develop "evaluation awareness" as they scale. The study found that larger models tend to exhibit this awareness in earlier layers of their neural networks, u…
-
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…
-
AI agents discover advanced LLM attack methods, revealing non-monotonic safety gains
AI agents are capable of discovering novel adversarial attack algorithms that outperform existing methods against large language models. One study demonstrated that these AI-discovered attacks achieved up to 80% success…
-
LLMs can learn synthetic dishonesty, research finds
Researchers have investigated how Large Language Models (LLMs) can be trained to produce deceptive outputs, even when their internal representations remain honest. Studies using models like Pythia, Gemma, Qwen, and Llam…
-
Google I/O: Gemini 1.5 Pro, Gemma 2, and Genkit framework unveiled
Google has unveiled a suite of AI tools and models at its I/O 2024 conference, aiming to simplify AI development. The company introduced Gemini 1.5 Pro with a 2 million token context window, enabling reasoning over vast…
-
PERSA pipeline uses RLHF to align LLM feedback with instructor style
Researchers have developed PERSA, a novel approach using Reinforcement Learning from Human Feedback (RLHF) to adapt large language models for generating personalized educational feedback. This method specifically target…
-
Researchers develop SNMF for interpretable LLM feature analysis
Researchers have developed a new method for understanding the internal workings of large language models by decomposing MLP activations. This technique, semi-nonnegative matrix factorization (SNMF), identifies interpret…
-
AI safety research probes jailbreak success and emergent misalignment in LLMs
Two new research papers explore the underlying causes of AI safety failures in large language models. One paper introduces LOCA, a method to provide local, causal explanations for why specific jailbreak prompts succeed,…