Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 10668
    Prev
    Next
    INDEX
    Explanations

    terms related to discounts and reductions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Arteta
    -0.67
    itanya
    -0.66
    ocarditis
    -0.65
    quelize
    -0.63
    rillation
    -0.63
    ctv
    -0.62
     Mann
    -0.61
     useCallback
    -0.61
     bed
    -0.60
     ak
    -0.60
    POSITIVE LOGITS
     discount
    1.21
     Discount
    1.11
     discounts
    1.09
    Discount
    1.06
    discount
    0.98
     discounted
    0.93
     Discounts
    0.87
     desconto
    0.86
     discounting
    0.83
    Discounts
    0.81
    Activations Density 0.075%

    No Known Activations