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. 2004
    Prev
    Next
    INDEX
    Explanations

    references to geometric shapes, specifically circles and related terms

    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
    ntax
    -0.86
     pitié
    -0.80
    +#+
    -0.79
    niest
    -0.77
    <thead>
    -0.77
     Fordham
    -0.76
    MenuInflater
    -0.75
    zczegól
    -0.73
    isiaj
    -0.73
     Mahomet
    -0.73
    POSITIVE LOGITS
     Circle
    2.40
     circle
    2.39
     CIRCLE
    2.27
     circles
    2.26
    Circle
    2.23
     Circles
    2.12
    circle
    2.11
    CIRCLE
    1.94
    circles
    1.93
    Circles
    1.92
    Activations Density 0.074%

    No Known Activations