© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105060
    Prev
    Next
    INDEX
    Explanations

    sequences of asterisks and other symbols that may indicate formatting or placeholders in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    AndEndTag
    -0.67
     estekak
    -0.66
    inSlope
    -0.63
     initComponents
    -0.63
     forState
    -0.61
    󠁿
    -0.61
     wireType
    -0.60
    CppMethod
    -0.60
    delwed
    -0.56
     deſſen
    -0.56
    POSITIVE LOGITS
    WillAppear
    0.36
    
    0.34
     emphasis
    0.33
    underbrace
    0.32
     underlying
    0.28
     Tint
    0.27
     förs
    0.27
    emphasis
    0.27
    <em>
    0.27
     steam
    0.27
    Activations Density 0.278%

    No Known Activations