© 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. 20-GEMMASCOPE-RES-131K
    11. 54110
    Prev
    Next
    INDEX
    Explanations

    terms associated with historical data records and backups

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

    version history and bypasses

    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
    Pou
    -0.32
     घ
    -0.29
     Seed
    -0.28
     Pou
    -0.28
    ตรี
    -0.27
     Seeds
    -0.27
    punkten
    -0.27
     tiết
    -0.26
     Adverti
    -0.26
     np
    -0.26
    POSITIVE LOGITS
    twimg
    0.79
    verwijspagina
    0.61
     Roskov
    0.60
    rungsseite
    0.57
     SwitchCompat
    0.56
    addCriterion
    0.56
     يتيمه
    0.56
    tanleria
    0.56
     replacement
    0.52
     autorytatywna
    0.52
    Activations Density 0.088%

    No Known Activations