© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 90753
    Prev
    Next
    INDEX
    Explanations

    time format specifications and representations

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

    minutes and seconds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     HasFactory
    -0.73
    MigrationBuilder
    -0.70
     NSCoder
    -0.68
    mobileqq
    -0.64
    niſſe
    -0.63
     informée
    -0.63
     nahilalakip
    -0.62
    AntiForgeryToken
    -0.61
     autorytatywna
    -0.61
    ftagPool
    -0.60
    POSITIVE LOGITS
    getMinutes
    0.49
    getSeconds
    0.40
     minutos
    0.37
    minute
    0.37
    time
    0.35
     minute
    0.33
    beat
    0.32
    Time
    0.30
    rate
    0.30
     minuto
    0.30
    Activations Density 0.016%

    No Known Activations