© 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. 20-GEMMASCOPE-RES-131K
    11. 20398
    Prev
    Next
    INDEX
    Explanations

    terms related to PDF management and software functionality

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

    partition manager, Mac, compatible devices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.73
    Tikang
    -0.69
     CURIAM
    -0.62
     تضيفلها
    -0.60
    expandindo
    -0.56
     سكانية
    -0.54
     Wiktionnaire
    -0.54
    CodeAnalysis
    -0.52
    RTCK
    -0.52
    ContentAsync
    -0.50
    POSITIVE LOGITS
    :✨
    0.35
    蒸
    0.32
    光
    0.32
     männis
    0.31
    Escolha
    0.29
     urusan
    0.28
     cioè
    0.28
     deals
    0.28
    uarine
    0.28
    Filler
    0.28
    Activations Density 0.015%

    No Known Activations