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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6093
    Prev
    Next
    INDEX
    Explanations

    JavaScript or jQuery method calls and syntax elements

    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
     Ulysses
    -0.77
     Tuk
    -0.70
    stre
    -0.70
     Bala
    -0.67
     Mooney
    -0.66
    неве
    -0.66
    Tow
    -0.64
    Iq
    -0.63
     Lewiston
    -0.62
    tanleria
    -0.62
    POSITIVE LOGITS
     ;
    0.98
     ;
    
    0.95
    alamus
    0.83
     &___
    0.83
    ;;;
    0.81
    ?>">
    0.78
     ;"
    0.78
     nè
    0.77
     initComponents
    0.75
    ;
    0.75
    Activations Density 0.125%

    No Known Activations