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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22-GEMMASCOPE-RES-16K
    6. 5955
    Prev
    Next
    INDEX
    Explanations

    references to food preparation and cultural practices related to cooking

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

    stores or sales

    np_acts-logits-general · gemini-2.0-flash

    clearance sales and discounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSCoder
    -0.67
    
    -0.65
    RetentionPolicy
    -0.64
    basicConfig
    -0.61
     protoimpl
    -0.57
     traductions
    -0.56
     davon
    -0.56
     distanciation
    -0.55
     كومونز
    -0.54
    Bookings
    -0.54
    POSITIVE LOGITS
     aisle
    0.69
     clearance
    0.65
     store
    0.63
    clearance
    0.60
     aisles
    0.58
     Clearance
    0.58
     associates
    0.58
    зулта
    0.57
    ItemBackground
    0.57
     associate
    0.52
    Activations Density 0.163%

    No Known Activations