Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 9650
    Prev
    Next
    INDEX
    Explanations

    the name "Mary" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gaston
    -0.77
     Luch
    -0.76
     Megal
    -0.72
     onFailure
    -0.70
     Dx
    -0.69
     Machu
    -0.69
     Mako
    -0.68
     Dapper
    -0.68
     Dox
    -0.68
     Perugia
    -0.68
    POSITIVE LOGITS
     Mary
    1.25
    MARY
    1.13
    Mary
    1.12
     MARY
    1.11
     María
    1.03
     Maryam
    1.02
     mary
    1.01
     Marys
    0.97
    María
    0.88
    mary
    0.87
    Activations Density 0.194%

    No Known Activations