© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6238
    Prev
    Next
    INDEX
    Explanations

    medical terminology and concepts related to anatomy and procedures

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

    location or proximity

    np_acts-logits-general · gemini-2.0-flash

    spatial relationships

    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
    tagHelperRunner
    -1.11
    SourceChecksum
    -0.82
     propOrder
    -0.79
    IndentedString
    -0.78
     EconPapers
    -0.72
    Datuak
    -0.71
    SequentialGroup
    -0.71
    GEBURTSDATUM
    -0.71
    InjectAttribute
    -0.70
     transférez
    -0.68
    POSITIVE LOGITS
     near
    2.00
    near
    1.57
     возле
    1.45
     behind
    1.43
    Near
    1.37
     beside
    1.34
     beneath
    1.32
     Near
    1.31
     underneath
    1.30
     outside
    1.27
    Activations Density 0.959%

    No Known Activations