© 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. 20-GEMMASCOPE-RES-16K
    6. 3532
    Prev
    Next
    INDEX
    Explanations

    references to specific types of plants and fruits, particularly olives and associated varieties

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

    Types of trees or wood

    np_acts-logits-general · gemini-2.0-flash

    trees, nuts, and plants

    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
    IntoConstraints
    -0.63
     cuivre
    -0.61
     onOptions
    -0.57
    ReusableCell
    -0.57
     amitié
    -0.54
     colère
    -0.54
    amitié
    -0.52
    umable
    -0.52
     griega
    -0.51
     öss
    -0.50
    POSITIVE LOGITS
     extract
    0.69
    Legături
    0.66
     blossom
    0.64
     trees
    0.62
     leaf
    0.62
     leaves
    0.62
    mappedBy
    0.61
     seed
    0.61
     Extract
    0.60
     juice
    0.60
    Activations Density 0.430%

    No Known Activations