© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12190
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to activate on a variety of things, including claims or assertions, musical notation, pizza, formal statements labeled with a number, and some mathematical notation, but the relationship between those things isn't super clear

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -1.27
    '
    -0.64
    ↵
    -0.54
    M
    -0.50
    li
    -0.49
    TC
    -0.48
    da
    -0.47
        
    -0.46
    ti
    -0.46
    ut
    -0.46
    POSITIVE LOGITS
     referenties
    0.77
    alagi
    0.71
    StoryboardSegue
    0.70
    exitRule
    0.70
    Демографія
    0.69
    Переваги
    0.69
    AGGIO
    0.69
    RUnlock
    0.68
    batore
    0.68
    Manbalar
    0.67
    Activations Density 3.286%

    No Known Activations