© 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. 32832
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks and string literals in code

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

    code punctuation and symbols

    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
    niſſe
    -0.94
    ロウィン
    -0.92
    ésultats
    -0.90
    ſelben
    -0.88
     ſuo
    -0.88
     fashiola
    -0.86
    ſammen
    -0.86
     ſua
    -0.85
    bildtitel
    -0.85
    [@BOS@]
    -0.84
    POSITIVE LOGITS
    w
    0.26
     letters
    0.25
     a
    0.25
    حيان
    0.25
    O
    0.24
    Y
    0.24
    =$?
    0.24
    Letters
    0.23
     che
    0.23
    o
    0.23
    Activations Density 0.155%

    No Known Activations