© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 90560
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references related to appeals and judicial decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    was issued

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initComponents
    -0.59
    providedIn
    -0.53
    WithIOException
    -0.52
    Personensuche
    -0.50
    windowFixed
    -0.47
    }{*}{
    -0.46
    NamedQueries
    -0.46
     trattano
    -0.45
    ソッド
    -0.44
     surla
    -0.44
    POSITIVE LOGITS
     issued
    1.17
     emiti
    1.00
     emitted
    0.95
     Issued
    0.95
    issued
    0.94
    Issued
    0.92
     issuing
    0.92
     uttered
    0.85
     issuance
    0.79
     ISSUED
    0.78
    Activations Density 0.451%

    No Known Activations