Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 668
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to legal proceedings and coercive actions

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

    discussions about force or coercion in the context of personal experiences

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

    forced or compelled

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     autorytatywna
    -0.78
    __*/
    -0.77
    UrlResolution
    -0.72
     <>",
    -0.72
    ThroughAttribute
    -0.69
    PreExecute
    -0.66
    ViewFeatures
    -0.66
    abetes
    -0.65
     الرياضيه
    -0.63
    sizeCache
    -0.63
    POSITIVE LOGITS
     forced
    2.06
     force
    2.06
    forced
    1.81
    force
    1.78
     Force
    1.78
     Forced
    1.72
     FORCE
    1.71
    Force
    1.69
    Forced
    1.68
     forcing
    1.63
    Activations Density 0.282%

    No Known Activations