© 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. 331
    Prev
    Next
    INDEX
    Explanations

    occurrences of the beginning of a text or new sections

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

    the beginning of sentences or paragraphs

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

    Captain America

    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
     
    -0.84
    -
    -0.64
     (
    -0.64
    ha
    -0.62
    le
    -0.61
     The
    -0.60
    1
    -0.60
     H
    -0.59
    th
    -0.59
    mon
    -0.58
    POSITIVE LOGITS
    MigrationBuilder
    2.71
     CreateTagHelper
    2.65
    IntoConstraints
    2.44
    GEBURTSDATUM
    2.42
    aarrggbb
    2.37
    ThroughAttribute
    2.36
     AssemblyCulture
    2.36
    RenderAtEndOf
    2.25
     unknownFields
    2.18
    contentLoaded
    2.18
    Activations Density 0.007%

    No Known Activations