© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105842
    Prev
    Next
    INDEX
    Explanations

    color-related terms and attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    transQ
    -0.91
    httphttps
    -0.80
    
    -0.79
     EconPapers
    -0.77
     <<<<<<<<<<<<<<
    -0.72
    RenderAtEndOf
    -0.71
     autorytatywna
    -0.70
    ########.
    -0.69
     nahilalakip
    -0.69
    ChildScrollView
    -0.68
    POSITIVE LOGITS
     color
    0.87
     colors
    0.82
     colour
    0.70
     colours
    0.69
    色
    0.63
     Colors
    0.62
     colored
    0.60
     couleur
    0.60
     light
    0.60
     white
    0.60
    Activations Density 0.183%

    No Known Activations