© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12480
    Prev
    Next
    INDEX
    Explanations

    This neuron appears to be firing on many kinds of math and technical notation, including programming, physics, and game scores.

    oai_token-act-pair · gemini-2.0-flash

    math and coding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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>
    -0.90
     bpy
    -0.65
     ISNI
    -0.58
    ThroughAttribute
    -0.53
    LElement
    -0.53
    Spy
    -0.53
     насељу
    -0.51
    StandardCharsets
    -0.50
    PyTuple
    -0.50
    endphp
    -0.50
    POSITIVE LOGITS
    GraphicsUnit
    0.65
     ModelExpression
    0.60
    ⓧ
    0.57
    Personendaten
    0.56
     =>
    0.54
    NameInMap
    0.54
     AssemblyCulture
    0.52
    줘
    0.52
    WithIOException
    0.52
    "]).
    0.50
    Activations Density 10.066%

    No Known Activations