Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-GEMMASCOPE-RES-16K
    6. 12844
    Prev
    Next
    INDEX
    Explanations

    references to the term "classical."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acute
    -0.82
     Acute
    -0.75
     Hoek
    -0.75
    emark
    -0.74
    Acute
    -0.72
     greateſt
    -0.71
     Brim
    -0.71
    ostante
    -0.70
     Majefty
    -0.69
     Acre
    -0.69
    POSITIVE LOGITS
    Classical
    1.85
     Classical
    1.82
     classical
    1.69
    classical
    1.66
     classica
    0.85
    古典
    0.81
    oporosis
    0.77
     clásica
    0.69
     nahilalakip
    0.64
    σχ
    0.64
    Activations Density 0.035%

    No Known Activations