© 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. 1372
    Prev
    Next
    INDEX
    Explanations

    ingredients and flavor descriptors related to food and cooking.

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

    descriptions related to the harvesting and production of olive oil.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    descriptive words for flavors and taste characteristics, particularly in relation to food and beverages.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    after prepositions or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    subtle flavors and notes

    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
    GeneratedCode
    -0.72
    IntoConstraints
    -0.57
    Slf
    -0.54
    printStackTrace
    -0.52
    出版年
    -0.52
    toMatchSnapshot
    -0.50
     presso
    -0.49
     superstitious
    -0.49
     dotenv
    -0.49
     ecológica
    -0.47
    POSITIVE LOGITS
     hints
    0.88
     subtle
    0.83
     hint
    0.82
     الرياضيه
    0.80
     Hints
    0.78
    hints
    0.75
     notes
    0.74
    subtle
    0.70
     moderate
    0.68
     balance
    0.66
    Activations Density 0.062%

    No Known Activations