© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1346
    Prev
    Next
    INDEX
    Explanations

    code-related constructs, specifically focusing on class definitions, methods, and their implementations in programming

    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
    
    -1.04
     ujednoznacz
    -0.92
     متعلقه
    -0.85
    
    -0.81
    IsContent
    -0.77
    AsUp
    -0.71
     ErrIntOverflow
    -0.71
    хьтан
    -0.70
    ########.
    -0.69
     ExecuteAsync
    -0.68
    POSITIVE LOGITS
     juges
    0.53
     kropp
    0.49
    ROUTINE
    0.49
    abadi
    0.49
     następujące
    0.46
     specifico
    0.46
     battu
    0.45
     llamo
    0.45
     sondern
    0.45
     zucca
    0.45
    Activations Density 0.525%

    No Known Activations