© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 16193
    Prev
    Next
    INDEX
    Explanations

    phrases and constructs that indicate choices or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    crollView
    -0.62
    MENAFN
    -0.50
    efeller
    -0.48
    ToBounds
    -0.48
    mybatisplus
    -0.48
     MRT
    -0.47
    forName
    -0.47
     hc
    -0.46
    hbase
    -0.46
    wirkungen
    -0.45
    POSITIVE LOGITS
     either
    1.23
    either
    1.17
    Either
    1.15
     Either
    1.09
     entweder
    0.91
    ITHER
    0.77
     либо
    0.69
    weder
    0.69
    ither
    0.66
     whichever
    0.63
    Activations Density 0.045%

    No Known Activations