© 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. 14869
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to performance measurements and resolutions in optical and electron-based imaging methods

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

    "high" followed by a measurement or quality

    np_acts-logits-general · gemini-2.0-flash

    high accuracy, resolution, sensitivity

    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
     autorytatywna
    -0.66
     dago
    -0.54
     iko
    -0.54
     saites
    -0.54
     Paglinawan
    -0.53
    IMPORTED
    -0.52
    AndEndTag
    -0.50
    ChildIndex
    -0.48
     Wirken
    -0.46
     éter
    -0.45
    POSITIVE LOGITS
     accuracy
    1.37
     precision
    1.24
    accuracy
    1.07
     resolution
    1.07
    Accuracy
    1.05
     Accuracy
    1.04
    precision
    0.96
     ACCUR
    0.94
     reliability
    0.93
     efficiency
    0.89
    Activations Density 1.436%

    No Known Activations