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. 9963
    Prev
    Next
    INDEX
    Explanations

    references to mathematical matrices

    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
     oignons
    -0.74
     Toul
    -0.74
     scarpe
    -0.74
    Calla
    -0.69
    isSuccessful
    -0.63
     taches
    -0.62
     Gogh
    -0.61
     giả
    -0.61
    ядок
    -0.60
    ibouti
    -0.60
    POSITIVE LOGITS
     nonatomic
    1.08
     PDS
    1.06
     matrices
    0.97
    nonatomic
    0.95
     Matrices
    0.88
     Matrix
    0.87
    RenderAtEndOf
    0.87
    Bibliograf
    0.85
    NonQuery
    0.84
    arie
    0.84
    Activations Density 0.082%

    No Known Activations