© 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. 3443
    Prev
    Next
    INDEX
    Explanations

    statistical results and their significance in medical research data

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

    Statistical significance: p-values

    np_acts-logits-general · gemini-2.0-flash

    percentage and p-value

    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
    RegisterType
    -0.43
     Vorg
    -0.41
     distanciation
    -0.41
    ことなく
    -0.40
     ...
    -0.39
     Con
    -0.38
     Lime
    -0.38
     Performance
    -0.38
    cmb
    -0.38
     calls
    -0.37
    POSITIVE LOGITS
    SequentialGroup
    1.09
     p
    0.90
    XmlAccessorType
    0.78
    bitField
    0.72
    AxisAlignment
    0.69
    __':
    0.69
    PageRoute
    0.66
    +:+
    0.65
    odds
    0.64
     AssemblyCulture
    0.63
    Activations Density 1.469%

    No Known Activations