© 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. 28-GEMMASCOPE-RES-16K
    11. 8529
    Prev
    Next
    INDEX
    Explanations

    events or activities involving social interactions and exchanges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    near restaurants or retail locations

    np_acts-logits-general · gemini-2.0-flash

    restaurants and retail

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sayfas
    -0.34
     Flugzeug
    -0.33
     projekty
    -0.31
    othelioma
    -0.31
     alliés
    -0.30
     prosjek
    -0.29
     medicina
    -0.29
     Fazit
    -0.28
     квартиры
    -0.28
    anyaan
    -0.28
    POSITIVE LOGITS
     restaurant
    1.27
     Restaurant
    1.13
     restaurants
    1.09
     retail
    1.08
    restaurant
    1.07
    Restaurant
    1.05
     Restaurants
    1.04
     Retail
    1.02
     RESTAURANT
    1.00
     restaurante
    0.98
    Activations Density 0.368%

    No Known Activations