© 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. 1432
    Prev
    Next
    INDEX
    Explanations

    quantitative data and comparisons in statistics

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

    large numeric percentages or statistical quantities.

    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
     лёг
    -0.35
     nggak
    -0.34
     légère
    -0.33
     kıs
    -0.33
    Шаг
    -0.32
     höch
    -0.31
     and
    -0.31
     âmes
    -0.31
     manchmal
    -0.31
     cebolla
    -0.31
    POSITIVE LOGITS
     resourceCulture
    1.03
     betweenstory
    0.75
     (>
    0.72
    Several
    0.66
     Several
    0.66
    数百
    0.65
    several
    0.63
     exceed
    0.63
    InputBorder
    0.62
     mxArray
    0.62
    Activations Density 0.185%

    No Known Activations