© 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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2603
    Prev
    Next
    INDEX
    Explanations

    markers indicating the beginning of a document or section

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

    special characters and start of document tokens (<bos>).

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    ftagPool
    -0.44
    setVerticalGroup
    -0.43
    énario
    -0.34
     tre
    -0.34
    texttt
    -0.33
     InputDecoration
    -0.32
     teach
    -0.32
    与此
    -0.32
     crises
    -0.31
     мира
    -0.31
    POSITIVE LOGITS
    Sqft
    1.03
    Халык
    0.60
    хьтан
    0.58
    reportWebVitals
    0.53
     ivelany
    0.52
     виправивши
    0.50
     EconPapers
    0.50
    :✨
    0.49
    ellees
    0.49
     queſta
    0.47
    Activations Density 0.001%

    No Known Activations