© 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 EvalsExportsinterp-engineNEWAPI 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. 7205
    Prev
    Next
    INDEX
    Explanations

    HTML form element attributes and metadata

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

    Followed by equals sign(s)

    np_acts-logits-general · gemini-2.0-flash

    name values

    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
    تقاوى
    -0.98
     '\\;'
    -0.82
     ویکی‌پدیا
    -0.73
    IsContent
    -0.71
    $_['
    -0.67
    PreferredItem
    -0.65
    Geplaatst
    -0.63
    AutoScaleMode
    -0.61
     trajets
    -0.60
    InstrumentedTest
    -0.59
    POSITIVE LOGITS
     кӀ
    0.61
    setVerticalGroup
    0.59
     asupra
    0.50
     متعلقه
    0.49
    WAR
    0.49
    ksom
    0.48
    nye
    0.48
     warmest
    0.48
    اء
    0.48
    gelöst
    0.47
    Activations Density 0.082%

    No Known Activations