© 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. 49349
    Prev
    Next
    INDEX
    Explanations

    programming-related terms or concepts

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

    express bonobo

    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
     geeignet
    -0.29
     ład
    -0.29
     eink
    -0.28
     مُعرِّف
    -0.28
    Concepto
    -0.28
     européens
    -0.28
     properly
    -0.26
     precioso
    -0.25
    Valores
    -0.25
    ylül
    -0.25
    POSITIVE LOGITS
    express
    1.56
    Express
    1.09
     express
    1.09
     Express
    1.05
     EXPRESS
    1.01
    EXPRESS
    1.00
     Numerade
    0.84
     defaultstate
    0.82
     autorytatywna
    0.77
    bootstrapcdn
    0.77
    Activations Density 0.000%

    No Known Activations