© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6510
    Prev
    Next
    INDEX
    Explanations

    references to circular and cylindrical shapes or structures

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

    circles, circular shapes, and radius

    np_acts-logits-general · gemini-2.0-flash

    radius and circular shapes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     koltuk
    -0.35
     véri
    -0.35
     puentes
    -0.34
    inigte
    -0.33
    jš
    -0.33
     zuges
    -0.33
     yük
    -0.32
     laborales
    -0.31
     cuarzo
    -0.31
    好
    -0.31
    POSITIVE LOGITS
     radius
    1.01
     circle
    0.95
     spherical
    0.95
     circles
    0.93
    Circle
    0.91
     Circle
    0.91
    radius
    0.91
     Spherical
    0.90
    circles
    0.90
    Circles
    0.89
    Activations Density 1.022%

    No Known Activations