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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 12090
    Prev
    Next
    INDEX
    Explanations

    references to diverse groups or samples in research studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewImports
    -0.85
    HandlerContext
    -0.56
    findpost
    -0.54
    #
    -0.53
    ,‎
    -0.52
    withId
    -0.51
    LEncoder
    -0.50
    SerializedName
    -0.50
    smell
    -0.50
    idiary
    -0.49
    POSITIVE LOGITS
     hundreds
    0.69
     dozens
    0.65
     thousands
    0.65
    hundreds
    0.61
     handful
    0.60
     thousand
    0.60
    thousands
    0.56
     nifer
    0.55
     hundred
    0.55
     multitudes
    0.55
    Activations Density 0.473%

    No Known Activations