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. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 109653
    Prev
    Next
    INDEX
    Explanations

    technical or mathematical symbols and terms, specifically those related to brackets and perforation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    观
    -0.52
    enumi
    -0.51
    觀
    -0.50
     Perfor
    -0.44
    ValueStyle
    -0.43
     hidráulica
    -0.40
     hidrá
    -0.39
     LaSalle
    -0.38
    perfor
    -0.38
    ViewImports
    -0.36
    POSITIVE LOGITS
     архивлан
    0.59
    MigrationBuilder
    0.57
    webElementXpaths
    0.57
    setVerticalGroup
    0.54
     للاسماء
    0.52
     '\\;'
    0.52
     useAppContext
    0.48
    windowFixed
    0.47
     Lutz
    0.47
    EDEFAULT
    0.46
    Activations Density 0.059%

    No Known Activations