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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 10937
    Prev
    Next
    INDEX
    Explanations

    elements related to programming constructs, specifically focusing on methods and properties in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enfans
    -0.68
     miniaturka
    -0.67
     Monfieur
    -0.66
     Reſ
    -0.62
     Perſ
    -0.60
     avoient
    -0.59
     myſelf
    -0.59
    ſelf
    -0.58
     ſta
    -0.58
     مشين
    -0.57
    POSITIVE LOGITS
    IntoConstraints
    0.59
    umbai
    0.45
     propOrder
    0.45
    Jeografia
    0.44
     smelt
    0.44
     Pneum
    0.44
    蚪
    0.44
     EU
    0.44
     gib
    0.43
     DIB
    0.43
    Activations Density 0.320%

    No Known Activations