© 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. 110166
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and operations involving data structures

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

    error handling of push requests

    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
    InputBorder
    -0.37
    contentLoaded
    -0.36
     незавершена
    -0.34
    createServer
    -0.34
     مش
    -0.34
    횟
    -0.33
    fetchall
    -0.30
    WireFormat
    -0.30
    ล้ว
    -0.30
    Enllaços
    -0.30
    POSITIVE LOGITS
     push
    0.83
    push
    0.80
     pushed
    0.78
     pushes
    0.72
     pushing
    0.69
     PUSH
    0.67
     Push
    0.67
    Push
    0.61
    pushed
    0.59
     Pushing
    0.58
    Activations Density 0.007%

    No Known Activations