© 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-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 8545
    Prev
    Next
    INDEX
    Explanations

    references to programming and software development concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adaptiveStyles
    -0.56
     propOrder
    -0.44
     Tür
    -0.40
    elemField
    -0.38
    日閲覧
    -0.36
    maire
    -0.36
    schlag
    -0.33
    ziej
    -0.33
    cydow
    -0.33
    感冒
    -0.32
    POSITIVE LOGITS
     OpenGL
    1.13
    OpenGL
    1.00
    opengl
    0.88
     Vulkan
    0.87
     GLFW
    0.81
     Graphics
    0.81
     Rendering
    0.80
     gl
    0.79
     GL
    0.78
     GPU
    0.77
    Activations Density 0.676%

    No Known Activations