Gemma Scope 2: Helping the AI Safety Community Deepen Understanding of Complex Language Model Behavior
Announcing a new, open suite of tools for language model interpretabilityLarge Language Models (LLMs) are capable of incredible feats of ...
Tag: Gemma
Google’s Gemma AI model helps discover new potential cancer therapy pathway
We gave our new C2S-Scale 27B model a task: Find a drug that acts as a conditional amplifier, one that ...
Introducing Gemma 3 270M: The compact model for hyper-efficient AI
The last few months have been an exciting time for the Gemma family of open models. We introduced Gemma 3 ...
Announcing Gemma 3n preview: powerful, efficient, mobile-first AI
Following the exciting launches of Gemma 3 and Gemma 3 QAT, our family of state-of-the-art open models capable of running ...
Flash 1.5, Gemma 2 and Project Astra
1.5 Flash excels at summarization, chat purposes, picture and video captioning, information extraction from lengthy paperwork and tables, and extra. ...
Gemma Scope: helping the safety community shed light on the inner workings of language models
Applied sciences Revealed 31 July 2024 Authors Language Mannequin Interpretability crew Saying a complete, open suite of sparse autoencoders for ...
