© 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. 10412
    Prev
    Next
    INDEX
    Explanations

    concepts related to authority and judgment

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

    after commas, especially "of" and "the"

    np_acts-logits-general · gemini-2.0-flash

    vision, control, map

    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
    awtextra
    -1.03
     мәкал
    -0.86
     للمعارف
    -0.82
     चीज़ों
    -0.81
    findpost
    -0.80
     >=",
    -0.79
     NSCoder
    -0.79
    ’”
    -0.78
    ’.”
    -0.76
    DockStyle
    -0.76
    POSITIVE LOGITS
     to
    0.79
     is
    0.78
    ,
    0.64
    -
    0.62
     of
    0.60
     in
    0.60
     are
    0.59
     --
    0.58
     –
    0.58
     can
    0.57
    Activations Density 0.165%

    No Known Activations