© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 780
    Prev
    Next
    INDEX
    Explanations

    phrases indicating scientific conclusions or summaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    érieures
    -0.39
     Sere
    -0.37
     especially
    -0.35
     Ersten
    -0.35
    posób
    -0.35
    ご存知
    -0.35
     Eintritt
    -0.34
     Zweiten
    -0.34
    ранее
    -0.34
    бычно
    -0.34
    POSITIVE LOGITS
     conclusion
    2.55
    Conclusion
    2.33
    conclusion
    2.23
     Conclusion
    2.22
     conclude
    2.00
    CONCLUSION
    2.00
     conclusions
    1.98
     CONCLUSION
    1.96
     conclusión
    1.95
     concludes
    1.91
    Activations Density 0.483%

    No Known Activations