© 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. 40-GEMMASCOPE-RES-16K
    11. 2126
    Prev
    Next
    INDEX
    Explanations

    promotional content related to discounts and coupons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     paznok
    -0.53
     Nail
    -0.50
     Hair
    -0.50
     nail
    -0.47
     ناخن
    -0.47
    Hair
    -0.46
    Nail
    -0.46
    指甲
    -0.45
     ネイル
    -0.45
    💇
    -0.44
    POSITIVE LOGITS
     pore
    0.65
     acne
    0.65
    AsUp
    0.64
     Pore
    0.62
     purging
    0.59
     breakout
    0.57
     pores
    0.57
     cystic
    0.56
     Acne
    0.54
     exfoli
    0.53
    Activations Density 0.266%

    No Known Activations