© 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. 18-GEMMASCOPE-RES-16K
    11. 14982
    Prev
    Next
    INDEX
    Explanations

    neurons related to programming and technical language

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

    Mathematical or unusual symbols

    np_acts-logits-general · gemini-2.0-flash

    technical terms and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </em>
    -0.49
     —
    -0.49
    يا
    -0.48
     =
    -0.47
    だけに
    -0.47
     morti
    -0.46
     #
    -0.46
    JI
    -0.46
     @
    -0.45
     .
    -0.45
    POSITIVE LOGITS
    TagMode
    0.92
    abestanden
    0.91
    Hochspringen
    0.88
    存于互联网档案馆
    0.87
     للمعارف
    0.82
    ViewImports
    0.82
    AutoresizingMask
    0.80
     ویکی‌پدیای
    0.79
     سكانية
    0.78
     Roskov
    0.78
    Activations Density 0.024%

    No Known Activations