© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 10419
    Prev
    Next
    INDEX
    Explanations

    topics related to dietary impacts and nutritional values

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

    "calories," "energy," or "kcal"

    np_acts-logits-general · gemini-2.0-flash

    dietary calories and energy

    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
     referenties
    -0.78
    verläs
    -0.55
    IsInitialized
    -0.52
    ittà
    -0.52
    물
    -0.52
    флек
    -0.50
    afone
    -0.49
    iroz
    -0.47
    opc
    -0.47
     Tind
    -0.47
    POSITIVE LOGITS
     calories
    1.65
     calorie
    1.39
     Calories
    1.32
     caloric
    1.27
    Calories
    1.22
     kalori
    1.16
    calories
    1.09
    calorie
    1.08
     calorías
    1.01
     kcal
    1.00
    Activations Density 0.123%

    No Known Activations