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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 814
    Prev
    Next
    INDEX
    Explanations

    references to GUI button components and their attributes in Java code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    numerusform
    -0.42
     трубы
    -0.40
     veckor
    -0.35
     Nachweis
    -0.35
     Verfahrens
    -0.35
    affaire
    -0.35
     easel
    -0.34
    affaires
    -0.34
     endwhile
    -0.32
    әрмәләр
    -0.32
    POSITIVE LOGITS
     Pressed
    0.77
     pressed
    0.77
    pressed
    0.71
     disabled
    0.70
     Disabled
    0.67
    Pressed
    0.66
    UpInside
    0.66
    disabled
    0.65
    Disabled
    0.63
     clicked
    0.62
    Activations Density 0.237%

    No Known Activations