© 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. 66564
    Prev
    Next
    INDEX
    Explanations

    variations of the word "prominent" to identify key subjects or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     auroit
    -0.63
    Algebra
    -0.61
     étoit
    -0.60
    cuela
    -0.59
     coû
    -0.57
     Mesin
    -0.55
    ValueStyle
    -0.55
     pouvoit
    -0.55
     feroit
    -0.54
     skola
    -0.54
    POSITIVE LOGITS
     prominent
    1.25
     prominently
    1.11
     prominence
    0.97
     promin
    0.91
    inent
    0.89
     significant
    0.70
     conspicuous
    0.70
     destacados
    0.69
    inence
    0.68
     destacado
    0.66
    Activations Density 0.006%

    No Known Activations