© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 120962
    Prev
    Next
    INDEX
    Explanations

    words that denote the capability or potential of something, often ending in "able."

    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
     Söz
    -0.52
     İş
    -0.52
    ckså
    -0.51
     Inscrivez
    -0.50
     strøm
    -0.49
     Misalnya
    -0.49
     auroit
    -0.48
    rungsseite
    -0.48
     ficha
    -0.48
    tymologie
    -0.48
    POSITIVE LOGITS
    izable
    0.78
    illable
    0.77
    ggable
    0.75
    entable
    0.73
    vable
    0.73
    ctable
    0.72
    orable
    0.70
    Sortable
    0.70
    ortable
    0.69
    atable
    0.68
    Activations Density 0.053%

    No Known Activations