© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8828
    Prev
    Next
    INDEX
    Explanations

    references to specific food items or dishes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.55
    kolen
    -0.55
    ództ
    -0.54
    itisation
    -0.53
    sø
    -0.52
    ]));
    
    -0.51
    İyi
    -0.51
    currentColor
    -0.51
    блиоте
    -0.51
    laszt
    -0.51
    POSITIVE LOGITS
     dish
    3.00
     dishes
    2.91
     Dishes
    2.63
     Dish
    2.58
     DISH
    2.40
    Dish
    2.40
    dish
    2.23
    Dishes
    2.19
    dishes
    2.08
     platos
    1.56
    Activations Density 0.046%

    No Known Activations