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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 20591
    Prev
    Next
    INDEX
    Explanations

    indicators of beginnings or initiations of actions

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

    starting an action

    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
     సౌకర్య
    -0.46
    ToProps
    -0.44
    ngths
    -0.44
     Dignity
    -0.43
     dignity
    -0.41
    ymas
    -0.41
     Würde
    -0.39
     DPRD
    -0.37
    adpleegd
    -0.37
     dignidad
    -0.35
    POSITIVE LOGITS
     up
    0.69
     working
    0.56
     out
    0.56
     talking
    0.54
     hitting
    0.53
    PYX
    0.52
     getting
    0.52
     playing
    0.51
     doing
    0.50
     thinking
    0.50
    Activations Density 0.021%

    No Known Activations