© 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. 70489
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation, specifically commas and dashes, indicating pauses or breaks in text

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

    words before comma

    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
     @{
    -0.48
    buttonShape
    -0.47
     quarts
    -0.43
    ouds
    -0.43
    ,
    -0.43
     gig
    -0.42
     Pads
    -0.41
     pinn
    -0.41
    miel
    -0.40
     pads
    -0.39
    POSITIVE LOGITS
     aikana
    0.68
    strado
    0.57
     avulla
    0.56
     during
    0.56
     gedurende
    0.55
     kanssa
    0.55
     Umfeld
    0.54
    during
    0.54
     kautta
    0.54
     ympä
    0.54
    Activations Density 0.136%

    No Known Activations