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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 36519
    Prev
    Next
    INDEX
    Explanations

    phrases related to bringing things or concepts to life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     isNameExpr
    -0.69
     للمعارف
    -0.61
     الحره
    -0.56
    ViewImports
    -0.56
     Paglinawan
    -0.55
     []:
    -0.52
     استنادى
    -0.52
    tanleria
    -0.51
     considér
    -0.49
    dafx
    -0.48
    POSITIVE LOGITS
     colorful
    0.63
     vivid
    0.56
     animated
    0.54
     color
    0.52
    animated
    0.52
     colors
    0.52
     visualized
    0.50
    vivid
    0.50
     viv
    0.49
    animate
    0.49
    Activations Density 0.004%

    No Known Activations