© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 5073
    Prev
    Next
    INDEX
    Explanations

    phrases and words that signal conclusions or summaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Sentences introducing conclusions

    np_acts-logits-general · gemini-2.0-flash

    conclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    posób
    -0.42
     Comprometido
    -0.40
     régulier
    -0.39
     ویکی‌پدی
    -0.38
     CanadaChoose
    -0.37
    heça
    -0.37
    Cyfarwyddwr
    -0.36
     igény
    -0.36
     ordinaire
    -0.35
     inimigo
    -0.35
    POSITIVE LOGITS
     conclusion
    2.09
    Conclusion
    1.95
     Conclusion
    1.88
    conclusion
    1.83
     concluding
    1.75
     conclude
    1.73
    CONCLUSION
    1.65
     conclusions
    1.62
     CONCLUSION
    1.62
     Conclusions
    1.56
    Activations Density 0.530%

    No Known Activations