© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 27264
    Prev
    Next
    INDEX
    Explanations

    code structure and declarations in programming languages

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

    code structure 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
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.68
     queſto
    -0.67
     laſſen
    -0.65
     unſer
    -0.64
     ſeine
    -0.64
    ſchaft
    -0.63
     indígen
    -0.61
     beſch
    -0.61
     メンテナ
    -0.61
    𑄮
    -0.61
    POSITIVE LOGITS
    ViewImports
    0.44
     AssemblyVersion
    0.33
     defaultstate
    0.30
    Vanjske
    0.29
    propTypes
    0.29
    Manbalar
    0.26
    gamb
    0.26
     gula
    0.26
    uxxxx
    0.26
    ')
    0.25
    Activations Density 0.004%

    No Known Activations