© 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. 13291
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their roles or contributions in specific contexts

    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
     diatas
    -1.12
     Whilst
    -1.10
     didalam
    -1.05
    Whilst
    -1.04
     loosing
    -1.02
     perchè
    -1.01
    慢慢的
    -1.00
     dimana
    -0.98
     skall
    -0.97
     whilst
    -0.94
    POSITIVE LOGITS
     postwar
    0.74
    ​—
    0.73
     Afterward
    0.71
     résumé
    0.68
     nonzero
    0.67
     ostensibly
    0.66
    更好地
    0.66
    说得
    0.66
    得太
    0.63
     به‌عنوان
    0.62
    Activations Density 3.745%

    No Known Activations