© 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. 15931
    Prev
    Next
    INDEX
    Explanations

    code structure elements and syntax

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

    Code snippets or programming syntax

    np_acts-logits-general · gemini-2.0-flash

    `ip` or `op` or `ast` or `md` or `py` or `vm` or `fn`

    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
    RectangleBorder
    -0.84
     betweenstory
    -0.76
    原始内容存档于
    -0.76
    InputBorder
    -0.74
     referrerpolicy
    -0.73
     lances
    -0.71
     للاسماء
    -0.71
     '\\;'
    -0.70
     AttributeError
    -0.70
    ApplicationTests
    -0.69
    POSITIVE LOGITS
    二是
    0.51
    HBox
    0.48
    voerd
    0.47
    laß
    0.46
    FromArgb
    0.46
     ň
    0.45
    setLine
    0.44
    tiary
    0.44
    Swiss
    0.44
     pecho
    0.43
    Activations Density 1.608%

    No Known Activations