© 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. 18-GEMMASCOPE-RES-16K
    6. 9174
    Prev
    Next
    INDEX
    Explanations

    phrases related to promotional offers and discounts

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

    deals or discounts

    np_acts-logits-general · gemini-2.0-flash

    advertised offers and promotions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.59
    المشاركات
    -0.54
    InjectAttribute
    -0.49
     Command
    -0.49
     παρά
    -0.48
    CloseOperation
    -0.48
    خاذ
    -0.48
    わりに
    -0.47
    inct
    -0.47
    gridy
    -0.46
    POSITIVE LOGITS
     offer
    0.92
     OFFER
    0.82
     offers
    0.81
     promotion
    0.81
    Offer
    0.79
     Offer
    0.76
     promo
    0.76
     advertised
    0.75
     offered
    0.74
     promotions
    0.72
    Activations Density 0.123%

    No Known Activations