Open interpretability tools for language models are now available across the entire Gemma 3 family with the release of Gemma Scope 2.
AI
Gemma Scope 2: helping the AI safety community deepen understanding of complex language model behavior
Google DeepMind · 2025-12-16
Related items
AIHugging Face Blog
Introducing Idefics2: A Powerful 8B Vision-Language Model for the community
AIGoogle DeepMind
AlphaGenome: AI for better understanding the genome
Introducing a new, unifying DNA sequence model that advances regulatory variant-effect prediction and promises to shed new light on genome function — now available via API.
AIHugging Face Blog
PaliGemma – Google's Cutting-Edge Open Vision Language Model
AIHugging Face Blog
NPHardEval Leaderboard: Unveiling the Reasoning Abilities of Large Language Models through Complexity Classes and Dynamic Updates
AIHugging Face Blog
SmolVLA: Efficient Vision-Language-Action Model trained on Lerobot Community Data
AIGoogle DeepMind
Introducing Gemma 3 270M: The compact model for hyper-efficient AI
Today, we're adding a new, highly specialized tool to the Gemma 3 toolkit: Gemma 3 270M, a compact, 270-million parameter model.