© 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. 63553
    Prev
    Next
    INDEX
    Explanations

    phrases indicating deadlines or due dates

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

    due to

    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
     ainfi
    -0.71
     commandement
    -0.69
    ſelf
    -0.63
     chrétien
    -0.62
     ciudadana
    -0.61
     enfans
    -0.60
     Grüsse
    -0.59
     plufieurs
    -0.59
     plastiques
    -0.57
     argint
    -0.56
    POSITIVE LOGITS
     due
    0.98
     DUE
    0.97
    due
    0.90
     Due
    0.90
    DUE
    0.87
    Due
    0.85
    dueDate
    0.72
    DueDate
    0.67
     duty
    0.66
     DUTY
    0.65
    Activations Density 0.022%

    No Known Activations