© 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. 34-GEMMASCOPE-RES-16K
    11. 3384
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and conditions related 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 @ 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
    Negative Logits
    SequentialGroup
    -0.48
    styleUrls
    -0.39
    Референце
    -0.38
    MLLoader
    -0.36
     scaricare
    -0.33
    ophor
    -0.33
     artig
    -0.29
     stij
    -0.29
     وتسجيلات
    -0.28
    خیص
    -0.28
    POSITIVE LOGITS
     lawsuit
    2.06
     lawsuits
    2.02
     litigation
    1.90
     sued
    1.84
     suing
    1.80
     litig
    1.59
     Litigation
    1.59
     suit
    1.50
     sue
    1.44
    itigation
    1.39
    Activations Density 1.739%

    No Known Activations