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. 1884
    Prev
    Next
    INDEX
    Explanations

    references to geographical and technical data in raster and vector formats

    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
     MainAxisSize
    -0.71
     للمعارف
    -0.71
     بيها
    -0.69
    UnusedPrivate
    -0.69
    WebVitals
    -0.63
    ద్య
    -0.61
    dollis
    -0.60
    InputChange
    -0.58
    setViewportView
    -0.57
    MenuGroup
    -0.57
    POSITIVE LOGITS
     maps
    0.87
     map
    0.77
     Maps
    0.71
    Maps
    0.71
     carto
    0.68
     aerial
    0.68
     mapa
    0.66
     mapping
    0.65
    maps
    0.64
    map
    0.64
    Activations Density 0.183%

    No Known Activations