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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2667
    Prev
    Next
    INDEX
    Explanations

    phrases related to culinary competition and critiques

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

    chefs or culinary topics

    np_acts-logits-general · gemini-2.0-flash

    chef and culinary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    曖昧さ回避
    -0.45
     vieilles
    -0.44
     manguera
    -0.43
     témoignage
    -0.43
     manteau
    -0.43
     témoin
    -0.43
     biens
    -0.42
     entanto
    -0.39
    okko
    -0.39
     mètre
    -0.38
    POSITIVE LOGITS
     chefs
    0.75
     culinary
    0.75
     chef
    0.75
     Chef
    0.73
     Chefs
    0.72
    Chef
    0.65
     cuisines
    0.63
     Culinary
    0.61
    chefs
    0.61
     culin
    0.60
    Activations Density 0.150%

    No Known Activations