# Activation Engineering Research

- **Event:** [Google Gemini Hackathon](https://cerebralvalley.ai/e/2025-ted-ai-hackathon)
- **When:** Oct 18 at 9:00 AM – Oct 19 at 5:00 PM (PDT)
- **Where:** Shack15, San Francisco, CA
- **Team:** [pramod thebe](https://cerebralvalley.ai/u/pthebe), [Severin Field](https://cerebralvalley.ai/u/sevdeawesome)
- **Demo video:** https://docs.google.com/document/d/12zJht6B2E34tJYGIeAGrcmUsrhvs7xgidUVCCkPE0OU/edit?usp=sharing
- **Gallery:** https://cerebralvalley.ai/e/2025-ted-ai-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/2025-ted-ai-hackathon/hackathon/gallery/29

OK, we decided to implement and then think of ideas for applying recent research to gemini!

Specifically, we read these 3 papers on representation engineering and activation patches-- steering model behavior by changing their internal representations

https://www.nature.com/articles/s44387-025-00031-9
https://arxiv.org/abs/2310.01405
https://arxiv.org/abs/2312.06681


One of us (sevi) did ml work to get this working in a way noone in research has yet, a sliding adjustable steering vector

---

Markdown version of https://cerebralvalley.ai/e/2025-ted-ai-hackathon/hackathon/gallery/29. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt