Smaller, Safer, More Transparent: Advancing Responsible AI with Gemma- Google Developers Blog

What this post added

Introduces Gemma 2 2B, a new 2 billion parameter model optimized for on-device deployment and efficiency, outperforming GPT-3.5 on the Chatbot Arena. Details its integration with NVIDIA TensorRT-LLM and availability on various hardware. Introduces ShieldGemma, a suite of safety content classifier models built on Gemma 2 to filter harmful AI inputs/outputs (hate speech, harassment, sexually explicit, dangerous content), offering flexible sizes (2B, 9B, 27B) and SOTA performance. Introduces Gemma Scope, a model interpretability tool using sparse autoencoders (SAEs) to analyze Gemma 2 2B and 9B models, with over 400 SAEs available and interactive demos on Neuronpedia.