© 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. 35499
    Prev
    Next
    INDEX
    Explanations

    headings and section titles in a document

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

    background and history

    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
    TestingModule
    -0.56
     endwhile
    -0.45
     قوله
    -0.40
    machus
    -0.35
    sendRedirect
    -0.34
    chließend
    -0.34
     farther
    -0.34
    これで
    -0.34
     moreover
    -0.33
     ayrıca
    -0.33
    POSITIVE LOGITS
    Overview
    0.75
     Background
    0.72
     Overview
    0.71
     background
    0.70
     history
    0.68
     geschiedenis
    0.68
     overview
    0.66
    Background
    0.64
    背景
    0.63
    overview
    0.62
    Activations Density 0.005%

    No Known Activations