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. 5-GEMMASCOPE-RES-16K
    6. 11740
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical frameworks and structures, specifically those involving Clifford algebras and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Massachusetts
    -1.21
     Boston
    -1.14
    Massachusetts
    -1.08
     Celtics
    -1.07
    Boston
    -1.05
    BOSTON
    -0.97
     Bruins
    -0.89
     BOSTON
    -0.83
     boston
    -0.80
     Cambridge
    -0.79
    POSITIVE LOGITS
    awtextra
    0.91
     المعيارى
    0.88
     Osborn
    0.84
     Watford
    0.81
     Latimer
    0.80
    aarrggbb
    0.79
    </caption>
    0.77
     للاسماء
    0.77
     Hama
    0.73
     Ambrose
    0.72
    Activations Density 1.698%

    No Known Activations