© 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 - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1325
    Prev
    Next
    INDEX
    Explanations

    the mention of the name "Mary."

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

    The name "Mary" and names following "Mary"

    np_acts-logits-general · gemini-2.0-flash

    Mary followed by a name or title

    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
    ExtendWith
    -0.66
    تقاوى
    -0.62
     ویکی‌پدیای
    -0.60
    withOpacity
    -0.58
     insuffisamment
    -0.57
     bağlantılar
    -0.56
     GenerationType
    -0.56
     estimés
    -0.53
     CURIAM
    -0.52
     pubblici
    -0.51
    POSITIVE LOGITS
    MARY
    0.70
     Mary
    0.68
    rschein
    0.67
     MARY
    0.66
    Mary
    0.62
     Marys
    0.59
     mary
    0.59
     Maryam
    0.58
    mary
    0.58
     createUser
    0.58
    Activations Density 0.080%

    No Known Activations