© 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. 6831
    Prev
    Next
    INDEX
    Explanations

    complex mathematical expressions and formulations

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

    Numbers followed by digits

    np_acts-logits-general · gemini-2.0-flash

    numbers and code fragments

    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
    WithFormat
    -0.74
     '{@
    -0.73
    enumi
    -0.72
    ment
    -0.72
     ]];
    -0.71
    ::::::::
    -0.70
    antMatchers
    -0.68
    UrlResolution
    -0.67
    netinet
    -0.66
     }}">
    -0.66
    POSITIVE LOGITS
    st
    1.04
    1
    0.92
    ⁄
    0.77
     StatefulWidget
    0.66
     referenties
    0.64
     Achille
    0.64
     Neel
    0.61
    eluaran
    0.61
     dieß
    0.60
    DAOImpl
    0.58
    Activations Density 0.511%

    No Known Activations