© 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 EvalsExportsinterp-engineNEWAPI 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. 34779
    Prev
    Next
    INDEX
    Explanations

    technical instructions related to API requests and the use of cURL

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

    curl commands

    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
    xically
    -0.32
     نف
    -0.32
     heapq
    -0.32
     XXXV
    -0.30
     препратки
    -0.30
    밌
    -0.30
    =$?
    -0.29
    upyter
    -0.29
     kiện
    -0.29
    Parade
    -0.29
    POSITIVE LOGITS
     curl
    0.71
     Curl
    0.65
    Curl
    0.62
    curl
    0.61
     CURLOPT
    0.58
     CURL
    0.55
     AssemblyTitle
    0.54
    zzleHttp
    0.54
     propOrder
    0.53
    CURLOPT
    0.52
    Activations Density 0.021%

    No Known Activations