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. 105195
    Prev
    Next
    INDEX
    Explanations

    commands and events related to user interface elements in a programming context

    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
    transQ
    -0.59
     '?'
    -0.57
    دانشنامهٔ
    -0.57
    BagLayout
    -0.57
     queſta
    -0.55
    pytest
    -0.54
    InjectAttribute
    -0.53
    AspNet
    -0.52
    `.`
    -0.51
    noopener
    -0.50
    POSITIVE LOGITS
     löyty
    0.64
     kokona
    0.59
     izquier
    0.57
     escuchado
    0.57
     cubierto
    0.56
     Keuangan
    0.56
     húmedo
    0.56
     skjø
    0.55
     oreja
    0.55
    hæng
    0.54
    Activations Density 0.004%

    No Known Activations