© 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
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12436
    Prev
    Next
    INDEX
    Explanations

    references to food groups and their dietary diversity

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

    Food groups and dietary components

    np_acts-logits-general · gemini-2.0-flash

    dietary food groups and patterns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ßerdem
    -0.39
     remuner
    -0.34
     Betrieb
    -0.34
    Sak
    -0.34
    bunifu
    -0.34
     Rptr
    -0.34
     corporate
    -0.33
    ache
    -0.33
     wasted
    -0.33
     du
    -0.32
    POSITIVE LOGITS
     foods
    0.92
     AssemblyCulture
    0.81
     meats
    0.80
    Foods
    0.77
     seafood
    0.71
     meat
    0.68
    foods
    0.68
     fruits
    0.66
     Foods
    0.66
     shellfish
    0.66
    Activations Density 0.368%

    No Known Activations