© 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. 83608
    Prev
    Next
    INDEX
    Explanations

    structural or syntactical elements in programming code

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

    code `= operators that can be followed by values`

    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
     réputation
    -0.40
    accompagnement
    -0.36
    LinearLayout
    -0.35
    sp
    -0.35
     Gilmour
    -0.34
     Corcoran
    -0.34
     paroi
    -0.34
     Ums
    -0.33
     bandoulière
    -0.33
    шков
    -0.33
    POSITIVE LOGITS
    StoryboardSegue
    0.73
    ymce
    0.66
    bine
    0.63
     للاسماء
    0.63
     Houſe
    0.62
    abe
    0.60
    gale
    0.60
    RTE
    0.60
     Rade
    0.60
    Portale
    0.60
    Activations Density 0.134%

    No Known Activations