© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7838
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to physics or engineering concepts

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

    Circle, radius, and related geometric concepts

    np_acts-logits-general · gemini-2.0-flash

    circle radius diameter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     propOrder
    -0.64
     ProtoMessage
    -0.56
    Stair
    -0.55
     समीक्षक
    -0.53
    horts
    -0.51
     esquer
    -0.50
     Trist
    -0.49
     iceberg
    -0.49
     stair
    -0.49
     Barak
    -0.48
    POSITIVE LOGITS
     circle
    1.80
     radius
    1.69
     Circle
    1.63
     circular
    1.61
    circle
    1.60
     circles
    1.59
    Circle
    1.56
     diameter
    1.50
     CIRCLE
    1.46
    radius
    1.43
    Activations Density 0.631%

    No Known Activations