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. 737
    Prev
    Next
    INDEX
    Explanations

    instances of the word "gather" and its variations, indicating a focus on collecting or assembling

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

    phrases related to gathering or assembling

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

    gathering and coming together

    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
    MigrationBuilder
    -0.99
     Meksiku
    -0.90
    lloworld
    -0.87
    حياتها
    -0.84
    ︎
    -0.82
     rootReducer
    -0.75
     ModelExpression
    -0.73
    UseVisualStyle
    -0.73
     AssemblyCulture
    -0.73
     disambiguazione
    -0.71
    POSITIVE LOGITS
    Gather
    1.03
     Gather
    0.97
     gather
    0.88
     gathers
    0.84
     Gathering
    0.80
     gathering
    0.78
    gather
    0.78
    Gathering
    0.77
     gathered
    0.71
     together
    0.67
    Activations Density 0.021%

    No Known Activations