© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 102121
    Prev
    Next
    INDEX
    Explanations

    references to gourmet food or dining experiences

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

    gourmet, Cantonese, cuisine

    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
     vectorielle
    -0.62
     Áng
    -0.52
     État
    -0.52
     plainte
    -0.51
     Jésus
    -0.50
     arbre
    -0.49
     Grèce
    -0.49
     ainfi
    -0.49
     fumée
    -0.49
     polaire
    -0.48
    POSITIVE LOGITS
     gourmet
    2.05
     Gourmet
    1.96
    Gour
    1.57
    gour
    1.41
     Gour
    1.10
     gour
    1.03
     gourmand
    0.98
     gastronom
    0.82
    グルメ
    0.81
     culinary
    0.76
    Activations Density 0.001%

    No Known Activations