© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 18143
    Prev
    Next
    INDEX
    Explanations

    references to pepper and its various forms or uses

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

    pepper

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vindt
    -0.37
    彡
    -0.36
    führen
    -0.35
    undial
    -0.34
     durchführen
    -0.33
     számára
    -0.33
     befind
    -0.33
     kunt
    -0.33
     Findlay
    -0.33
     Hild
    -0.33
    POSITIVE LOGITS
     pepper
    2.00
     Pepper
    1.44
    pepper
    1.42
    Pepper
    1.30
     peppers
    1.17
     pimienta
    1.12
     poivre
    1.07
     Peppers
    0.96
     перец
    0.88
    胡椒
    0.86
    Activations Density 0.002%

    No Known Activations