© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 27057
    Prev
    Next
    INDEX
    Explanations

    mentions of the UTC time zone

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

    UTC and GMT time

    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
     kysy
    -0.40
    ių
    -0.37
     paneles
    -0.35
     élector
    -0.35
    KommentareTeilen
    -0.35
     Shao
    -0.34
    örder
    -0.34
    ĝis
    -0.34
    ském
    -0.34
     ollut
    -0.33
    POSITIVE LOGITS
     UTC
    1.29
    UTC
    1.25
    utc
    0.92
     GMT
    0.89
    GMT
    0.87
     utc
    0.86
    Utc
    0.84
     gmt
    0.73
    InteropServices
    0.64
     onlyOwner
    0.60
    Activations Density 0.003%

    No Known Activations