© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 61720
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to web server communication and AJAX requests

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

    web server 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
    MemberId
    -0.36
     Casey
    -0.35
     araştır
    -0.33
     zbior
    -0.31
    TaskList
    -0.31
     Walk
    -0.31
     ensayo
    -0.31
    experimental
    -0.30
    Walk
    -0.30
     harian
    -0.30
    POSITIVE LOGITS
     server
    0.97
    HtmlAttribute
    0.87
     Server
    0.84
     AJAX
    0.84
    WebServlet
    0.81
     HTML
    0.79
     HTTP
    0.79
    Server
    0.77
     serveur
    0.77
    MessageTagHelper
    0.75
    Activations Density 0.212%

    No Known Activations