© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 120
    Prev
    Next
    INDEX
    Explanations

    biographical information about individuals, specifically their professions and attributes

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

    information about prominent individuals and their professions

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

    American people and professions

    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
    elerik
    -0.66
    Климат
    -0.66
    oa̍t
    -0.65
    Externé
    -0.63
    henge
    -0.62
    ]++;
    -0.59
    MigrationBuilder
    -0.59
    المشاركات
    -0.58
     "}";
    -0.57
     الاطلاع
    -0.56
    POSITIVE LOGITS
     actor
    0.75
     Actor
    0.69
     singer
    0.66
     actress
    0.65
    American
    0.64
    Actor
    0.63
     famous
    0.61
     American
    0.61
     professional
    0.60
     born
    0.60
    Activations Density 0.126%

    No Known Activations