© 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. 9044
    Prev
    Next
    INDEX
    Explanations

    numerical values and potential errors in numerical data contexts

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

    "18 U.S.C. §" followed by a number

    np_acts-logits-general · gemini-2.0-flash

    numbers after 2

    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
     McGovern
    -0.84
    :///
    -0.72
    EClass
    -0.71
     Werth
    -0.71
    orship
    -0.70
    "],
    -0.69
    prehensive
    -0.69
    ✎
    -0.68
     lạc
    -0.68
    hasOwnProperty
    -0.67
    POSITIVE LOGITS
    nd
    1.25
    2
    1.09
     thirds
    0.94
    thirds
    0.83
    0
    0.80
    gether
    0.75
    som
    0.70
    5
    0.69
     Ronde
    0.67
     linseed
    0.67
    Activations Density 0.595%

    No Known Activations