© 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. 8983
    Prev
    Next
    INDEX
    Explanations

    specific medical or scientific terminology and concepts

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

    Followed by conjunctions (and, while, whereas)

    np_acts-logits-general · gemini-2.0-flash

    whereas, while, respectively

    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
    ScopeManager
    -0.63
     CreateTagHelper
    -0.56
    itus
    -0.51
    pulseira
    -0.50
    protoimpl
    -0.49
     noqa
    -0.49
    DoubleQuotes
    -0.48
    TagMode
    -0.48
    ganza
    -0.46
    tesi
    -0.46
    POSITIVE LOGITS
     whereas
    3.25
     while
    2.86
    whereas
    2.85
     Whereas
    2.69
     tandis
    2.68
    Whereas
    2.57
    while
    2.52
     sedangkan
    2.45
     mentre
    2.35
     mientras
    2.28
    Activations Density 1.092%

    No Known Activations