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. 10116
    Prev
    Next
    INDEX
    Explanations

    occurrences and variations of the word "of."

    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
    goku
    -0.53
    dataTables
    -0.52
     Stockholm
    -0.49
    webp
    -0.45
     templado
    -0.44
    殊
    -0.44
    getLine
    -0.44
     Tats
    -0.44
    Pessoa
    -0.44
    द्र
    -0.43
    POSITIVE LOGITS
    ########.
    1.05
    ftagPool
    0.78
     StatefulWidget
    0.78
    StructEnd
    0.77
    enumi
    0.76
     kasarigan
    0.75
    MessageOf
    0.75
    Хьажоргаш
    0.74
    IGraphics
    0.73
    TintMode
    0.73
    Activations Density 0.810%

    No Known Activations