© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7036
    Prev
    Next
    INDEX
    Explanations

    The neuron is highly activated by numeric tokens—especially multi-digit numbers and decimal values (e.g. monetary or measurement figures).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ")
    0.66
     }}}
    0.65
     }}
    0.64
    </h3>
    0.63
     }}=\
    0.62
    }}}\
    0.61
    ,:)
    0.61
     "}
    0.61
    }}}=\
    0.58
     }.
    0.57
    POSITIVE LOGITS
    ^{*}$
    1.39
    ^*$
    1.27
    }$;
    1.20
    ^{+}$
    1.20
    _{*}$
    1.20
    \}$
    1.17
    }$,
    1.16
    }$
    1.16
    )$,
    1.16
    _{-}$
    1.13
    Activations Density 0.064%

    No Known Activations