© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10709
    Prev
    Next
    INDEX
    Explanations

    references to meals, specifically dinner

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

    "dinner."

    np_acts-logits-general · gemini-2.0-flash

    dinner and social events

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     magnétique
    -0.53
     polaire
    -0.51
     financiero
    -0.49
     policiales
    -0.49
     légende
    -0.48
     capuz
    -0.47
     digitais
    -0.47
     caneta
    -0.47
     izquierdo
    -0.47
     sindical
    -0.47
    POSITIVE LOGITS
     dinner
    1.76
    Dinner
    1.66
     Dinner
    1.66
    dinner
    1.58
     DINNER
    1.44
     dinners
    1.39
     meal
    1.36
     meals
    1.20
     Meal
    1.17
    Meal
    1.16
    Activations Density 0.101%

    No Known Activations