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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 114584
    Prev
    Next
    INDEX
    Explanations

    exit commands in code

    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
     kasarigan
    -0.63
    RepeatedField
    -0.60
     isNameExpr
    -0.57
     ModelRenderer
    -0.56
     ddelweddau
    -0.55
    richTextPanel
    -0.54
     CURLOPT
    -0.54
    -------
    -0.54
     Lino
    -0.54
     للمعارف
    -0.53
    POSITIVE LOGITS
    exit
    0.60
    stdlib
    0.52
    EXIT
    0.44
     reflexión
    0.40
    Exit
    0.40
     reflexão
    0.39
    وفاته
    0.39
    addGap
    0.37
    PYX
    0.37
     exit
    0.36
    Activations Density 0.003%

    No Known Activations