© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 9799
    Prev
    Next
    INDEX
    Explanations

    dates and timestamps in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.78
     Roskov
    -0.75
    sizeCache
    -0.74
    ThroughAttribute
    -0.74
    XmlAccessType
    -0.72
     Référence
    -0.69
     StatefulWidget
    -0.69
    SourceChecksum
    -0.68
    numerusform
    -0.68
    runApp
    -0.68
    POSITIVE LOGITS
     Nov
    1.51
     Jul
    1.50
     Dec
    1.49
     Oct
    1.45
    Dec
    1.34
     Aug
    1.29
    Nov
    1.26
     Jun
    1.25
     Apr
    1.22
     Feb
    1.21
    Activations Density 0.075%

    No Known Activations