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 - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 64
    Prev
    Next
    INDEX
    Explanations

    instances of conditional statements, specifically switch cases in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isNameExpr
    -0.63
     isNameExpr
    -0.60
     itſelf
    -0.59
     cdti
    -0.59
     [];
    
    -0.57
    PreInfinity
    -0.56
     "];
    -0.55
     INTERESAR
    -0.54
     Conſ
    -0.53
     StatefulWidget
    -0.53
    POSITIVE LOGITS
    switch
    0.74
    styleType
    0.63
     insuffisamment
    0.56
    ʁ
    0.55
    enumi
    0.55
    WireFormat
    0.53
    testify
    0.53
    hagic
    0.53
    Jeden
    0.50
    ंदीखरीदारी
    0.50
    Activations Density 0.019%

    No Known Activations