© 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. 12290
    Prev
    Next
    INDEX
    Explanations

    references to specific legal cases or legal citations

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

    Apostrophes followed by "s"

    np_acts-logits-general · gemini-2.0-flash

    legal citations and programming terms

    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
    ↵
    -0.69
    </strong>
    -0.58
    ↵↵↵
    -0.50
    </em>
    -0.49
    ^
    -0.47
    ../
    -0.45
    <eos>
    -0.45
    }{
    -0.43
    +
    -0.42
    Rep
    -0.42
    POSITIVE LOGITS
    findpost
    0.94
    脚注の使い方
    0.86
    saraba
    0.77
     estekak
    0.76
    UnsafeEnabled
    0.74
    ftagPool
    0.74
    BeginContext
    0.74
    AndEndTag
    0.72
    CloseOperation
    0.72
    roek
    0.72
    Activations Density 0.043%

    No Known Activations