© 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. 42661
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to engineering and invention

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    multilingual words and punctuation

    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
    Negative Logits
    uxxxx
    -0.95
    ValueStyle
    -0.88
     transfieras
    -0.83
     ProtoMessage
    -0.79
     autorytatywna
    -0.79
    IsMutable
    -0.78
     للمعارف
    -0.77
     zwiſchen
    -0.76
     disambiguazione
    -0.75
     queſta
    -0.75
    POSITIVE LOGITS
     zufolge
    0.32
     Photocase
    0.31
     bepaalde
    0.28
     língua
    0.27
     Bemerkungen
    0.27
     aquello
    0.26
     gewöhn
    0.26
     yalnızca
    0.25
     bertambah
    0.25
    følgelig
    0.25
    Activations Density 0.147%

    No Known Activations