© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 95484
    Prev
    Next
    INDEX
    Explanations

    references to weeks and temporal indicators in data or reports

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

    week timing

    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
     doğum
    -0.35
     miej
    -0.33
     Catholic
    -0.32
     âmes
    -0.32
     dzisiaj
    -0.32
     heuti
    -0.30
     dziś
    -0.30
     ワイン
    -0.29
     Geschichts
    -0.29
     فريبيس
    -0.28
    POSITIVE LOGITS
    Week
    1.34
    week
    1.31
     week
    1.26
     Week
    1.17
    weeks
    1.15
    WEEK
    1.14
     WEEK
    1.09
    Weeks
    1.05
     weeks
    1.05
     semaine
    1.02
    Activations Density 0.021%

    No Known Activations