© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 10460
    Prev
    Next
    INDEX
    Explanations

    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 @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    خاذ
    -0.56
     فريبيس
    -0.54
    IContainer
    -0.52
     intptr
    -0.51
    aurais
    -0.49
    doria
    -0.49
    InjectAttribute
    -0.48
    lış
    -0.45
     Signalez
    -0.45
     "..\..\..\
    -0.44
    POSITIVE LOGITS
     promo
    1.00
     promotions
    0.98
     discounts
    0.98
     coupon
    0.95
     savings
    0.94
     promotion
    0.92
     discount
    0.91
    promo
    0.90
     Promo
    0.87
     promos
    0.87
    Activations Density 0.106%

    No Known Activations