© 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. 9-GEMMASCOPE-RES-131K
    11. 125137
    Prev
    Next
    INDEX
    Explanations

    references to time intervals or frequency, particularly those related to monthly occurrences

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

    monthly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aislado
    -0.50
     isolé
    -0.48
     voulons
    -0.47
     isolado
    -0.47
     wiesz
    -0.46
     Wissenschaften
    -0.46
     adaptés
    -0.46
     Fassung
    -0.45
    ckså
    -0.44
     vård
    -0.44
    POSITIVE LOGITS
     monthly
    1.97
     Monthly
    1.93
    Monthly
    1.82
    monthly
    1.79
     MONTHLY
    1.66
     mensual
    1.13
    每月
    1.09
     monat
    1.09
    MONTH
    1.03
     mensuales
    1.02
    Activations Density 0.004%

    No Known Activations