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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 16353
    Prev
    Next
    INDEX
    Explanations

    references to hands and their positions or usage

    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
     Италијани
    -0.52
    parsedMessage
    -0.52
    Personensuche
    -0.47
    новниш
    -0.45
    efined
    -0.45
     idéia
    -0.44
    tvguidetime
    -0.43
    StreetMap
    -0.42
    asteroide
    -0.42
    basicConfig
    -0.41
    POSITIVE LOGITS
     hand
    0.48
     HAND
    0.47
    hand
    0.47
    DockStyle
    0.44
    IContainer
    0.43
     dimenti
    0.43
    GIVEREF
    0.42
     Hand
    0.42
    Hand
    0.42
    complexContent
    0.41
    Activations Density 0.012%

    No Known Activations