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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 12616
    Prev
    Next
    INDEX
    Explanations

    financial or numerical expressions and data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.52
     وتسجيلات
    -0.47
     (
    
    -0.43
    '
    
    -0.42
     "
    
    -0.42
     ([]
    -0.42
     passim
    -0.41
    xodo
    -0.41
    </i>
    -0.41
    こうした
    -0.41
    POSITIVE LOGITS
    ГЛА
    0.77
    sizeCache
    0.76
    Personensuche
    0.74
    DebuggerStep
    0.73
     ModelExpression
    0.71
     createSprite
    0.71
    Datuak
    0.70
    ounid
    0.68
    matchCondition
    0.68
    parsedMessage
    0.68
    Activations Density 0.313%

    No Known Activations