© 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
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 10980
    Prev
    Next
    INDEX
    Explanations

    food-related items and cooking references

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

    before common punctuation or HTML

    np_acts-logits-general · gemini-2.0-flash

    dishes and ingredients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.49
    fahrene
    -0.48
    atorship
    -0.48
     lentejuelas
    -0.47
     kapture
    -0.46
    ssä
    -0.45
     ویکی‌پدی
    -0.44
     châssis
    -0.44
    новниш
    -0.44
    astify
    -0.43
    POSITIVE LOGITS
     seafood
    0.62
     cheese
    0.60
     potatoes
    0.60
     pasta
    0.59
     cheeses
    0.58
     fried
    0.57
     steaks
    0.57
     chicken
    0.57
     bacon
    0.56
     meat
    0.55
    Activations Density 0.334%

    No Known Activations