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. 0-GEMMASCOPE-RES-16K
    6. 8154
    Prev
    Next
    INDEX
    Explanations

    repetitive control flow structures and line numbers in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \{\\
    -0.99
    felves
    -0.76
     doubtnut
    -0.76
     للمعارف
    -0.74
     arşivlendi
    -0.74
    ',
    
    
    -0.73
    arschijnlijk
    -0.72
    argout
    -0.72
    [])
    
    -0.72
    )•
    -0.72
    POSITIVE LOGITS
    while
    0.79
    UnusedPrivate
    0.63
    where
    0.60
     InputDecoration
    0.54
    y
    0.52
    LikeLiked
    0.50
    usus
    0.48
    .
    0.47
    elemField
    0.47
    field
    0.47
    Activations Density 0.253%

    No Known Activations