© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1346
    Prev
    Next
    INDEX
    Explanations

    instances of definitions, examples, and excerpts in the text

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

    Words/phrases that follow "taken"

    np_acts-logits-general · gemini-2.0-flash

    obtained from sources

    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
    asgi
    -0.59
    findpost
    -0.59
    WriteBarrier
    -0.54
    intenant
    -0.53
     marquées
    -0.52
    imwrite
    -0.52
    SpringRunner
    -0.52
    enfone
    -0.52
     fermés
    -0.52
    IContainer
    -0.51
    POSITIVE LOGITS
     borrowed
    1.57
     taken
    1.45
     extracted
    1.44
    taken
    1.35
     copied
    1.27
     adapted
    1.26
    borrow
    1.26
    extracted
    1.24
     sourced
    1.23
     excerpts
    1.22
    Activations Density 0.654%

    No Known Activations