© 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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14122
    Prev
    Next
    INDEX
    Explanations

    references to dietary ingredients and nutritional content in animal studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DoubleQuotes
    -0.69
    RectangleBorder
    -0.68
     jScrollPane
    -0.64
     وتسجيلات
    -0.59
     ujednoznacz
    -0.57
     صوتيه
    -0.56
    +#+#
    -0.56
    onViewCreated
    -0.56
     radon
    -0.53
    hoeddwyd
    -0.53
    POSITIVE LOGITS
     feeding
    1.37
     feed
    1.36
     diet
    1.25
     feeds
    1.25
     Feeding
    1.15
    feeding
    1.14
     Feed
    1.13
    Feeding
    1.09
     diets
    1.09
    feed
    1.08
    Activations Density 0.321%

    No Known Activations