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

    Neuronpedia

    Jacobian LensNEW
    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. 33-GEMMASCOPE-RES-16K
    11. 6898
    Prev
    Next
    INDEX
    Explanations

    occurrences of structured summaries and conclusions in scientific texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rocz
    -0.36
     ویکی‌پدی
    -0.36
    érieures
    -0.36
    tigungs
    -0.35
     Stephenson
    -0.34
    posób
    -0.34
     Sere
    -0.34
    Reprodução
    -0.34
    ご存知
    -0.33
     Gläub
    -0.33
    POSITIVE LOGITS
     conclusion
    2.58
     summary
    2.34
    Conclusion
    2.33
    conclusion
    2.27
     Conclusion
    2.27
     Summary
    2.14
     conclude
    2.11
    Summary
    2.08
     conclusions
    2.06
    CONCLUSION
    2.02
    Activations Density 0.787%

    No Known Activations