© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 708
    Prev
    Next
    INDEX
    Explanations

    mentions of specific non-verbalized classes or categories, particularly focusing on scientific terms and designations

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

    terms related to technical or scientific classifications and categorizations

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

    nonsurgical, nonsingular, nonsponge

    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
    Personensuche
    -0.82
    CloseOperation
    -0.81
    moiselle
    -0.76
    complexContent
    -0.76
    endphp
    -0.75
     autorytatywna
    -0.71
    ssohn
    -0.69
    edicated
    -0.69
    MigrationBuilder
    -0.69
     Europeo
    -0.67
    POSITIVE LOGITS
    os
    0.53
    ys
    0.52
    rs
    0.52
    ese
    0.52
    cons
    0.52
    avas
    0.51
    itos
    0.51
    ges
    0.49
     Mus
    0.49
    az
    0.49
    Activations Density 0.853%

    No Known Activations