© 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. 36-GEMMASCOPE-RES-16K
    11. 15591
    Prev
    Next
    INDEX
    Explanations

    specific scientific measurements and data references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BoxShadow
    -0.36
     linkovi
    -0.33
    unehmen
    -0.33
     فار
    -0.33
    threat
    -0.33
    icitis
    -0.32
    unteer
    -0.32
     sna
    -0.31
     Timeline
    -0.30
     SUD
    -0.30
    POSITIVE LOGITS
     fitted
    0.79
     fits
    0.78
     fit
    0.77
     uncertainties
    0.73
     fitting
    0.73
     deduced
    0.71
     corrected
    0.69
    fitted
    0.69
     derived
    0.67
     inferred
    0.67
    Activations Density 1.674%

    No Known Activations