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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 2329
    Prev
    Next
    INDEX
    Explanations

    instances of the word "capture" and its variations, indicating a focus on the act of recording or obtaining information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ioutil
    -0.53
    的呢
    -0.50
    ficulties
    -0.50
    AntiForgeryToken
    -0.50
    TTT
    -0.49
    wertig
    -0.47
     TTT
    -0.47
     goof
    -0.46
     Troubles
    -0.46
     resultList
    -0.46
    POSITIVE LOGITS
     capture
    1.06
    capture
    1.02
    Capture
    0.97
     Capture
    0.95
     captured
    0.94
     capturar
    0.94
     capturing
    0.93
     captures
    0.91
    CAPTURE
    0.87
     captura
    0.85
    Activations Density 0.128%

    No Known Activations