Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 5946
    Prev
    Next
    INDEX
    Explanations

    terms related to food service and dining experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.72
    省市镇
    -0.72
    SourceChecksum
    -0.71
    awtextra
    -0.68
    RegistryLite
    -0.67
    LLocation
    -0.67
    isContained
    -0.67
    enumi
    -0.66
    WithIdentifier
    -0.66
    ukone
    -0.63
    POSITIVE LOGITS
     food
    0.60
     orders
    0.59
     delivery
    0.56
     takeout
    0.56
     pesanan
    0.55
     kitchen
    0.54
     shop
    0.54
    Food
    0.52
     menu
    0.52
    food
    0.51
    Activations Density 0.085%

    No Known Activations