© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 81835
    Prev
    Next
    INDEX
    Explanations

    instances of actions being taken or referred to in a legal context

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

    doing things

    np_acts-logits-general · gemini-2.5-flash-lite

    It detects mentions of legal or administrative actions or proceedings (references to taking, reviewing, or remanding an action).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.48
    RotationOrder
    -0.44
    úly
    -0.41
    NamedQueries
    -0.38
    MigrationBuilder
    -0.38
    EndInit
    -0.36
    bulkan
    -0.36
    BitConverter
    -0.36
    WriteAttribute
    -0.35
     getProduct
    -0.35
    POSITIVE LOGITS
     actions
    0.77
    getAction
    0.73
     action
    0.72
     acción
    0.71
     Schritte
    0.69
     Handlungen
    0.69
     Actions
    0.68
    action
    0.68
    行為
    0.67
     действия
    0.66
    Activations Density 0.245%

    No Known Activations