© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 63261
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods and commas

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

    Proper authors' names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mijne
    -0.36
     fís
    -0.35
     zařízení
    -0.34
     fisik
    -0.31
     huom
    -0.31
     moeder
    -0.31
    for
    -0.30
     Statistik
    -0.30
     begge
    -0.30
     sendok
    -0.29
    POSITIVE LOGITS
     Roskov
    1.13
     propOrder
    0.87
     kasarigan
    0.82
     autorytatywna
    0.79
     فريبيس
    0.75
    OGND
    0.74
     ſind
    0.73
    ロウィン
    0.72
    wiliwch
    0.71
    Билгалдахарш
    0.70
    Activations Density 0.001%

    No Known Activations