© 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. 82903
    Prev
    Next
    INDEX
    Explanations

    programming code elements that involve exclusion and data manipulation

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

    excluding modifiers or properties

    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
     suficientemente
    -0.31
    utuhkan
    -0.30
     appropriately
    -0.29
     tilbage
    -0.29
     jemand
    -0.27
     compatible
    -0.27
     apropi
    -0.26
     Vereinigten
    -0.26
     appropriate
    -0.25
     näch
    -0.25
    POSITIVE LOGITS
    featureID
    0.86
     unnecessary
    0.81
    RTEX
    0.79
    CodeAttribute
    0.76
     للاسماء
    0.74
     inneces
    0.74
     superfluous
    0.73
    unknownFields
    0.72
    keyColumn
    0.69
     tartalomajánló
    0.69
    Activations Density 0.030%

    No Known Activations