© 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. 9-GEMMASCOPE-RES-16K
    11. 8242
    Prev
    Next
    INDEX
    Explanations

    terms related to geometric shapes and spatial dimensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    geometrical terms related to circular shapes and measurements, particularly focusing on radius and radial coordinates.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     protoimpl
    -0.43
     begrü
    -0.40
    iliation
    -0.39
     muere
    -0.37
     arbejds
    -0.37
     lær
    -0.36
    warp
    -0.35
    veck
    -0.35
    work
    -0.35
     desaparecer
    -0.35
    POSITIVE LOGITS
     radius
    1.14
     radii
    0.97
    Radius
    0.97
    radius
    0.94
     Radius
    0.93
     diameter
    0.85
     radial
    0.79
     RADIUS
    0.78
    Radial
    0.77
     Diameter
    0.76
    Activations Density 0.655%

    No Known Activations