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 - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 36599
    Prev
    Next
    INDEX
    Explanations

    instances of error handling in code or comments related to HTTP requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    SequentialGroup
    -0.56
    chevêque
    -0.54
     this
    -0.51
    uesia
    -0.50
     bağlantılar
    -0.50
    ColumnInfo
    -0.48
     voilà
    -0.47
    FileDialog
    -0.46
     put
    -0.44
    verwijspagina
    -0.44
    POSITIVE LOGITS
    Lähteet
    0.89
    UnusedPrivate
    0.77
    UIControlState
    0.70
     _('
    0.69
     _("
    0.69
     المعيارى
    0.67
     "..\..\
    0.66
    itinéraire
    0.65
    ("}");
    0.64
     HttpNotFound
    0.64
    Activations Density 0.019%

    No Known Activations