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. 20-GEMMASCOPE-RES-16K
    6. 13903
    Prev
    Next
    INDEX
    Explanations

    phrases related to discounts and promotional offers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.55
    awtextra
    -0.54
     Pseud
    -0.52
     pseud
    -0.52
    queryInterface
    -0.50
    ContentLoaded
    -0.50
    siębior
    -0.49
     BoxFit
    -0.49
     posX
    -0.48
    ContentAlignment
    -0.48
    POSITIVE LOGITS
     discounts
    2.14
     discount
    2.08
     discounted
    1.86
     Discounts
    1.74
    discount
    1.71
     Discount
    1.65
    Discounts
    1.61
     discounting
    1.59
    Discount
    1.55
     diskon
    1.41
    Activations Density 0.189%

    No Known Activations