© 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-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 10440
    Prev
    Next
    INDEX
    Explanations

    terms related to promotions and marketing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cau
    -0.54
    newtheorem
    -0.54
     TextInputType
    -0.53
    GetMapping
    -0.51
    handleRequest
    -0.48
    sbin
    -0.47
    الت
    -0.47
    plist
    -0.47
    abcdef
    -0.45
    entid
    -0.45
    POSITIVE LOGITS
    promo
    1.15
     promotion
    1.13
     promo
    1.04
     promotions
    1.02
     Promotion
    1.00
    Promotion
    1.00
     Promo
    0.98
     Promotions
    0.95
    promotion
    0.94
     promos
    0.94
    Activations Density 0.071%

    No Known Activations