© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 102385
    Prev
    Next
    INDEX
    Explanations

    concepts related to legal terms and procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     décret
    -0.33
    anzug
    -0.30
     political
    -0.30
     suced
    -0.30
     Pas
    -0.30
    立
    -0.29
     mó
    -0.28
     pas
    -0.28
    büro
    -0.28
    lapsingToolbar
    -0.28
    POSITIVE LOGITS
    endpush
    0.73
     exfoli
    0.64
    endphp
    0.63
     nahilalakip
    0.61
    AndEndTag
    0.61
    expandindo
    0.60
    WebElementEntity
    0.60
    //
    0.60
     dermat
    0.59
     EconPapers
    0.59
    Activations Density 0.004%

    No Known Activations