© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 7860
    Prev
    Next
    INDEX
    Explanations

    references to food and its related topics

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

    the word "food"

    np_acts-logits-general · gemini-2.0-flash

    food insecurity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hard
    -0.57
    =$?
    -0.57
    posedge
    -0.54
     HARD
    -0.53
     Pfund
    -0.51
    hard
    -0.50
     tvrd
    -0.49
    ecore
    -0.49
     harder
    -0.49
    AssignableFrom
    -0.48
    POSITIVE LOGITS
    Food
    0.81
     food
    0.80
     Food
    0.76
    food
    0.76
    FOOD
    0.73
    makanan
    0.71
     FOOD
    0.70
    stuff
    0.68
     foods
    0.68
    KommentareTeilen
    0.67
    Activations Density 0.202%

    No Known Activations