© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3301
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to discounts and promotional offers

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

    references to discounts and percentages off.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     policiales
    -0.46
     pernas
    -0.41
     Policía
    -0.39
     ciała
    -0.37
     caixas
    -0.36
    Biographie
    -0.36
     gavetas
    -0.36
     atividades
    -0.36
    isAlive
    -0.35
    ：“……”
    -0.35
    POSITIVE LOGITS
     Discount
    0.87
     discount
    0.83
     discounts
    0.78
    AddTagHelper
    0.78
    discount
    0.76
    Discount
    0.75
     Discounts
    0.69
    isContained
    0.65
     descuento
    0.61
    :+:
    0.61
    Activations Density 0.167%

    No Known Activations