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. 71
    Prev
    Next
    INDEX
    Explanations

    programming constructs and syntax related to function and method definitions in code

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

    symbols and syntax related to programming, particularly in the context of function definitions and file operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     fris
    -0.62
    migrationBuilder
    -0.48
     Fris
    -0.47
     Government
    -0.47
    fante
    -0.46
     conference
    -0.46
    Fris
    -0.46
    اه
    -0.46
     Conference
    -0.46
    keli
    -0.45
    POSITIVE LOGITS
    operator
    0.96
     operator
    0.81
     OPERATOR
    0.71
    Filmografie
    0.65
    StoryboardSegue
    0.63
     Operator
    0.62
    queryInterface
    0.61
    (*
    0.60
     بيها
    0.60
     operador
    0.59
    Activations Density 0.059%

    No Known Activations