© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15952
    Prev
    Next
    INDEX
    Explanations

    commands and definitions related to graphical user interface dimensions and layouts

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

    Code that defines sizes or measurements

    np_acts-logits-general · gemini-2.0-flash

    CGSize width and height

    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
    -0.93
    Hochspringen
    -0.91
    AxisAlignment
    -0.74
    WebElementEntity
    -0.70
     Italijani
    -0.69
    قایناقلار
    -0.69
    دانشنامهٔ
    -0.69
    PyExc
    -0.68
     kasarigan
    -0.66
    RUnlock
    -0.66
    POSITIVE LOGITS
     CGSize
    0.53
     measurements
    0.46
    SizeF
    0.46
    ClientSize
    0.42
    ográficas
    0.42
    miary
    0.41
    intrinsic
    0.41
     intrinsic
    0.41
    świet
    0.41
     measured
    0.41
    Activations Density 0.017%

    No Known Activations