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-2-2B
    4. Residual Stream - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1837
    Prev
    Next
    INDEX
    Explanations

    scientific terms and measurements related to biological processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Демографія
    -0.58
    DockStyle
    -0.57
    ChildIndex
    -0.56
    saraba
    -0.55
     Signalez
    -0.54
     AssemblyCulture
    -0.54
    TagMode
    -0.52
     pinulongan
    -0.52
    getItemId
    -0.50
     Akismet
    -0.50
    POSITIVE LOGITS
     فريبيس
    0.68
    expandindo
    0.63
    ScopeManager
    0.60
    sizeCache
    0.59
     للمعارف
    0.57
    ftagPool
    0.57
    InSection
    0.56
     TÉCNICA
    0.55
    Aiheesta
    0.54
     nearby
    0.52
    Activations Density 0.373%

    No Known Activations