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. 90121
    Prev
    Next
    INDEX
    Explanations

    code segments and compiler directives related to programming and variable declarations

    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
    原始内容
    -0.34
    原始内容存档于
    -0.34
     Schulze
    -0.33
     isNameExpr
    -0.33
    它们的
    -0.32
    <h3>
    -0.31
     stessa
    -0.30
     settlements
    -0.30
    <em>
    -0.29
    <code>
    -0.28
    POSITIVE LOGITS
    SEGUIR
    0.63
    bootstrapcdn
    0.63
    setViewportView
    0.62
    ImageContext
    0.62
    lgari
    0.61
     propOrder
    0.60
     चीज़ों
    0.59
    igslist
    0.58
    addGap
    0.58
    IVEREF
    0.57
    Activations Density 0.052%

    No Known Activations