© 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. 4556
    Prev
    Next
    INDEX
    Explanations

    generic code structures and functions

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

    Java or Android code snippets

    np_acts-logits-general · gemini-2.0-flash

    programming types and methods

    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
     pri
    -0.53
     above
    -0.52
     EventArgs
    -0.48
    QApplication
    -0.47
    BorderFactory
    -0.47
    mybatisplus
    -0.43
     n
    -0.42
    extAlignment
    -0.42
    setupUi
    -0.42
    BorderLayout
    -0.41
    POSITIVE LOGITS
    int
    0.94
     الحره
    0.84
    final
    0.83
    boolean
    0.81
     int
    0.75
    #+#
    0.75
     بيها
    0.73
    String
    0.72
    Portály
    0.72
    ernalia
    0.70
    Activations Density 0.120%

    No Known Activations