© 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
    2. Gemma-2-2B
    3. 6-GEMMASCOPE-TRANSCODER-16K
    4. 15088
    Prev
    Next
    INDEX
    Explanations

    This neuron detects information about competitive games, including specific scores (e.g., "2-1"), words related to winning (e.g., "defeat"), and terms associated with sports (e.g., "halftime').

    oai_token-act-pair · gemini-2.0-flash

    sports scores

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    "});
    -0.49
    '});
    -0.46
    ).'
    -0.45
    "})
    -0.44
    ())))
    -0.44
    "};
    -0.44
    .'"
    -0.43
    ]."
    -0.43
    )."
    -0.42
    '));
    -0.42
    POSITIVE LOGITS
    principalColumn
    0.76
    ⓧ
    0.74
    ViewFeatures
    0.74
    GEBURTSDATUM
    0.73
    HomeAsUpEnabled
    0.73
     surla
    0.72
    NameInMap
    0.70
    GraphicsUnit
    0.70
    पया
    0.69
    NewUrlParser
    0.66
    Activations Density 9.655%

    No Known Activations