© 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. 70802
    Prev
    Next
    INDEX
    Explanations

    the presence of punctuation marks, indicating the end of statements or questions

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

    finally

    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
     الحره
    -0.69
    Jeografia
    -0.68
     utafitiHapana
    -0.67
    exitRule
    -0.66
     autorytatywna
    -0.66
     فريبيس
    -0.65
    posedge
    -0.63
    richTextPanel
    -0.62
    Tikang
    -0.61
     ویکی‌پدی
    -0.59
    POSITIVE LOGITS
     finalmente
    0.42
    iertamente
    0.38
    Formazione
    0.36
     TAMBÉM
    0.36
     Finally
    0.35
    よいよ
    0.34
     virkelig
    0.34
    diğinde
    0.34
    illigen
    0.34
    azen
    0.33
    Activations Density 0.154%

    No Known Activations