© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11136
    Prev
    Next
    INDEX
    Explanations

    references to gift cards and their associated entitlements

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

    Promotional offers, discounts, or rewards

    np_acts-logits-general · gemini-2.0-flash

    coupon codes and vouchers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     voors
    -0.43
     oprot
    -0.40
     strijd
    -0.37
     exemplaires
    -0.36
     hierba
    -0.36
    setVerticalGroup
    -0.35
     kleuren
    -0.34
     mukana
    -0.34
     kiin
    -0.34
     aurez
    -0.33
    POSITIVE LOGITS
     voucher
    0.54
     coupons
    0.52
     kasarigan
    0.51
     coupon
    0.50
     tickets
    0.50
     vouchers
    0.49
    Voucher
    0.48
    findpost
    0.48
     بگ
    0.48
     arşivlendi
    0.47
    Activations Density 0.123%

    No Known Activations