© 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. 20-GEMMASCOPE-RES-16K
    11. 13120
    Prev
    Next
    INDEX
    Explanations

    nutritional ingredients and their potential health benefits

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

    associated with healthy or vegan food

    np_acts-logits-general · gemini-2.0-flash

    yogurt and smoothie ingredients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.64
    UserScript
    -0.59
     ujednoznacz
    -0.59
    gants
    -0.57
    oredCriteria
    -0.54
    dì
    -0.52
     cbr
    -0.52
     cigarette
    -0.51
     препратки
    -0.50
    entown
    -0.50
    POSITIVE LOGITS
     organic
    1.01
     vegan
    0.94
     healthy
    0.92
     quinoa
    0.91
     smoothies
    0.88
     Quinoa
    0.88
     smoothie
    0.87
     detox
    0.86
     Detox
    0.85
     healthier
    0.84
    Activations Density 0.133%

    No Known Activations