© 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. 6976
    Prev
    Next
    INDEX
    Explanations

    technical specifications and methods related to electronic components and their manufacturing processes

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

    Followed by verbs in passive voice

    np_acts-logits-general · gemini-2.0-flash

    be/is/are/to + verb/adjective

    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
    invokeLater
    -0.62
    Tikang
    -0.61
    Manbalar
    -0.55
     jScrollPane
    -0.54
    equalsIgnoreCase
    -0.51
    块钱
    -0.51
     Phaser
    -0.49
    angliski
    -0.48
    readObject
    -0.48
    ArrowToggle
    -0.48
    POSITIVE LOGITS
    الدراسه
    0.71
     الرياضيه
    0.61
    참고
    0.61
     ①
    0.60
    inafter
    0.59
    ①
    0.59
     gug
    0.59
     hoge
    0.59
    ≒
    0.59
    hereinafter
    0.58
    Activations Density 1.687%

    No Known Activations