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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 45835
    Prev
    Next
    INDEX
    Explanations

    words related to different types of peppers and spicy ingredients

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

    pepper and related spices

    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
    encanaan
    -0.43
     detalladas
    -0.42
     SwitchCompat
    -0.41
     schwerer
    -0.40
    clat
    -0.39
    inkscape
    -0.38
    Lähteet
    -0.38
     Flüssigkeit
    -0.38
     Visconti
    -0.38
    klärung
    -0.38
    POSITIVE LOGITS
     pepper
    1.09
     Pepper
    0.95
    Pepper
    0.92
     paprika
    0.88
    pepper
    0.85
     Cayenne
    0.84
     pimienta
    0.83
     poivre
    0.81
     peppers
    0.77
     Peppers
    0.77
    Activations Density 0.028%

    No Known Activations