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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8988
    Prev
    Next
    INDEX
    Explanations

    references to food in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.39
     rodilla
    -0.35
    lyse
    -0.34
     harvesting
    -0.34
    jy
    -0.33
     harvest
    -0.33
    pass
    -0.33
     tùy
    -0.33
    issing
    -0.33
    atissimo
    -0.33
    POSITIVE LOGITS
     food
    2.73
    food
    2.44
     Food
    2.44
    Food
    2.39
     FOOD
    2.30
    FOOD
    2.16
     foods
    1.72
     voedsel
    1.61
    食物
    1.58
    foods
    1.55
    Activations Density 0.108%

    No Known Activations