© 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-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 57511
    Prev
    Next
    INDEX
    Explanations

    references to time intervals, particularly focusing on years and related durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.72
     myö
    -0.68
    Hentet
    -0.66
     kés
    -0.59
    engertian
    -0.58
    หมือน
    -0.57
    ГЛА
    -0.57
     Mérimée
    -0.56
     gants
    -0.56
     joka
    -0.55
    POSITIVE LOGITS
    PerformLayout
    0.78
     اخیر
    0.71
     recent
    0.67
     fince
    0.66
     Vergangenheit
    0.64
     momenta
    0.64
     decade
    0.63
    ี่ยม
    0.63
     (;;)
    0.62
    (;;)
    0.61
    Activations Density 0.026%

    No Known Activations