© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 104287
    Prev
    Next
    INDEX
    Explanations

    references to construction and repair work activities

    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
    migrationBuilder
    -0.47
     TextAppearance
    -0.46
     cucchia
    -0.44
    tilhar
    -0.43
     transparencia
    -0.40
     imprensa
    -0.40
     Duft
    -0.40
     Gegenwart
    -0.39
     hybrids
    -0.39
     brands
    -0.39
    POSITIVE LOGITS
     repairs
    0.62
     getService
    0.56
     tasks
    0.56
     Repairs
    0.56
     repair
    0.55
     작업
    0.54
     lavori
    0.54
     work
    0.53
    repair
    0.53
     ремонт
    0.52
    Activations Density 0.017%

    No Known Activations