© 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 - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 8475
    Prev
    Next
    INDEX
    Explanations

    specific locations and establishments related to food and beverage experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Matériau
    -0.50
    Matériau
    -0.46
     cinturón
    -0.43
     témoin
    -0.42
     dôle
    -0.41
     chirurgie
    -0.40
     dignité
    -0.40
     pauvreté
    -0.40
    jącej
    -0.39
    יע
    -0.39
    POSITIVE LOGITS
     brewery
    0.84
     beer
    0.84
     beers
    0.79
     breweries
    0.77
     brewers
    0.77
     brew
    0.74
     brewer
    0.71
     brewed
    0.70
     brews
    0.67
     brewing
    0.65
    Activations Density 0.059%

    No Known Activations