© 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. 106007
    Prev
    Next
    INDEX
    Explanations

    references to vegetarian options and adaptability in menu items

    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
    gunaan
    -0.27
     growth
    -0.27
    iteurs
    -0.27
     onderhoud
    -0.27
    úgó
    -0.26
     fédé
    -0.25
     regioni
    -0.25
    numerusform
    -0.25
     lay
    -0.25
     formel
    -0.25
    POSITIVE LOGITS
    CUSTOM
    0.73
     CUSTOM
    0.71
    Customization
    0.71
     Customization
    0.68
     насељу
    0.68
    custom
    0.67
     customized
    0.66
    Custom
    0.65
     custom
    0.65
    customized
    0.65
    Activations Density 0.048%

    No Known Activations