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. 73643
    Prev
    Next
    INDEX
    Explanations

    terms related to technical specifications and performance metrics

    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
    bcryptjs
    -0.57
    )‏
    -0.48
    LookAnd
    -0.47
    IMPORTED
    -0.47
     jSON
    -0.44
    ContentAsync
    -0.42
    ❶
    -0.42
     appart
    -0.41
    <thead>
    -0.41
    ScopeManager
    -0.41
    POSITIVE LOGITS
    Eglise
    0.71
     poichè
    0.63
     Bewußt
    0.63
    pecabe
    0.62
     avoient
    0.61
     feroit
    0.60
     Gutierrez
    0.60
     viata
    0.60
     hendes
    0.59
     idéia
    0.59
    Activations Density 0.076%

    No Known Activations