© 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. 38-GEMMASCOPE-RES-16K
    11. 7724
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific comparisons and associations among variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tembelea
    -0.56
    RegressionTest
    -0.55
     незавершена
    -0.52
     otomatig
    -0.49
    Diwedd
    -0.48
    nameof
    -0.47
    mergeFrom
    -0.46
    MENAFN
    -0.46
    Hauptartikel
    -0.45
     botto
    -0.45
    POSITIVE LOGITS
     strong
    0.89
     differences
    0.86
     remarkable
    0.85
     considerable
    0.85
     marked
    0.79
     similarities
    0.78
     différences
    0.75
     pronounced
    0.73
     significant
    0.73
     slight
    0.73
    Activations Density 2.123%

    No Known Activations