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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 14
    Prev
    Next
    INDEX
    Explanations

    references to date and time formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to date and time data types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    date and time or adult male

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    chafter
    -0.73
     Савезне
    -0.71
     ExecuteAsync
    -0.66
    icoot
    -0.61
    ός
    -0.61
    Попис
    -0.60
    ruik
    -0.60
     للاسماء
    -0.59
    зулта
    -0.59
     Roskov
    -0.58
    POSITIVE LOGITS
    Offset
    0.81
     noct
    0.63
     dateTime
    0.61
    ScopeManager
    0.59
     gili
    0.56
     lapse
    0.56
    στη
    0.54
    uthor
    0.53
     Erlebnis
    0.51
    AutoresizingMask
    0.51
    Activations Density 0.004%

    No Known Activations