© 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. 63301
    Prev
    Next
    INDEX
    Explanations

    elements associated with library and include statements in programming

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

    .h and .hpp files

    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
     noDo
    -0.81
     oprot
    -0.76
    matchCondition
    -0.73
    RenderAtEndOf
    -0.71
    Personendaten
    -0.70
     zuſammen
    -0.69
     zwiſchen
    -0.68
     ſehen
    -0.68
    SharedDtor
    -0.68
     queſta
    -0.68
    POSITIVE LOGITS
    printStackTrace
    0.34
     girasol
    0.32
    uarga
    0.32
    stack
    0.30
     Staff
    0.29
     mochila
    0.28
     provisoire
    0.27
    PerformLayout
    0.26
    report
    0.26
    stdio
    0.26
    Activations Density 0.010%

    No Known Activations