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. 117408
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific measurements and experimental conditions

    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
     eş
    -0.35
     fér
    -0.34
    stock
    -0.33
     Arzt
    -0.32
     cenas
    -0.32
     segu
    -0.32
     puesta
    -0.32
     państw
    -0.32
     Kau
    -0.31
     verdade
    -0.31
    POSITIVE LOGITS
     ProtoMessage
    0.78
     transfieras
    0.71
    Попис
    0.68
    tagHelperRunner
    0.68
     nakalista
    0.61
     estekak
    0.60
     uLocal
    0.59
    addCriterion
    0.57
    UrlResolution
    0.56
     jspb
    0.55
    Activations Density 0.171%

    No Known Activations