© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 6107
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to lawsuits

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     nature
    -0.40
    ophor
    -0.36
    <table>
    -0.33
    </thead>
    -0.32
     times
    -0.32
     arithmetic
    -0.31
     elog
    -0.30
     imparted
    -0.29
     brim
    -0.29
     arts
    -0.29
    POSITIVE LOGITS
     lawsuit
    0.76
     sued
    0.70
     lawsuits
    0.69
     suing
    0.68
    SharedDtor
    0.66
     Litigation
    0.56
     litigation
    0.56
     lawyer
    0.55
    UnitTesting
    0.54
     litig
    0.54
    Activations Density 1.993%

    No Known Activations