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. 25-GEMMASCOPE-RES-16K
    6. 1928
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and structures related to ideals and their properties in algebra

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SARAH
    -0.71
     Curt
    -0.71
     Constantine
    -0.68
     Cron
    -0.67
     Buddy
    -0.66
     Sarah
    -0.66
     Kristen
    -0.65
     Foley
    -0.65
     Pash
    -0.65
     NSCoder
    -0.64
    POSITIVE LOGITS
     Collins
    0.97
    Collins
    0.83
     تضيفلها
    0.78
     COLLINS
    0.77
     Malik
    0.75
     Murillo
    0.72
     MenuView
    0.72
     Camden
    0.72
     Blum
    0.71
     Nio
    0.71
    Activations Density 1.400%

    No Known Activations