© 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. 6365
    Prev
    Next
    INDEX
    Explanations

    references to product features and benefits

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

    product details and specifications, especially for technical or consumer goods.

    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
    Havolalar
    -0.35
    Eksteraj
    -0.35
     potential
    -0.34
    ();*/
    -0.34
    logeny
    -0.34
     tấn
    -0.33
    前言
    -0.33
    '>";
    -0.32
    ユニクロ
    -0.32
     ton
    -0.31
    POSITIVE LOGITS
     ujednoznacz
    0.63
    suitable
    0.53
     Paglinawan
    0.52
    sizeCache
    0.51
    xnn
    0.51
     kasarigan
    0.49
    AutoField
    0.49
    bright
    0.49
    Chham
    0.48
    queryInterface
    0.48
    Activations Density 0.078%

    No Known Activations