© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 31580
    Prev
    Next
    INDEX
    Explanations

    expressions and structures related to optional values or fields in programming languages

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

    consequently mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     /\.(
    -0.71
     Freitas
    -0.60
    adaptiveStyles
    -0.59
    CLO
    -0.59
     архивлан
    -0.57
     WV
    -0.54
    ixas
    -0.52
     RK
    -0.51
    ("#{
    -0.50
     Kea
    -0.50
    POSITIVE LOGITS
    帖最后由
    0.78
    хьтан
    0.77
     Réponses
    0.71
    apunov
    0.69
    Распо
    0.69
     surla
    0.68
     venons
    0.66
    🤣🤣
    0.64
    iedenis
    0.63
    []]
    0.63
    Activations Density 0.006%

    No Known Activations