© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4227
    Prev
    Next
    INDEX
    Explanations

    references to promotional offers and discounts related to products

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

    "Coupon" or skincare related text

    np_acts-logits-general · gemini-2.0-flash

    skincare coupon codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fumée
    -0.43
     plancher
    -0.42
     carburant
    -0.40
     hambre
    -0.40
     leña
    -0.39
    Bicycle
    -0.38
    FailureListener
    -0.38
    Wiring
    -0.38
     nucléaire
    -0.38
     viande
    -0.37
    POSITIVE LOGITS
     skincare
    1.05
     dermat
    0.85
     dermatologist
    0.84
     Skincare
    0.80
     skin
    0.79
     Skin
    0.74
     acne
    0.71
    Skin
    0.69
     SKIN
    0.68
    skin
    0.68
    Activations Density 0.170%

    No Known Activations