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. 131028
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "bootstrap" in various contexts

    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
    y
    -0.41
    ">//
    -0.33
     espécie
    -0.33
    <h2>
    -0.32
    Y
    -0.31
    万人
    -0.31
    Abitanti
    -0.31
    Denny
    -0.31
    QMetaType
    -0.31
     MessageBoxIcon
    -0.31
    POSITIVE LOGITS
    Bootstrap
    1.38
     Bootstrap
    1.38
     bootstrap
    1.38
    bootstrap
    1.34
     bootstra
    1.15
     BOOT
    0.88
     Boot
    0.77
    BOOT
    0.77
    boot
    0.73
     BOO
    0.73
    Activations Density 0.006%

    No Known Activations