© 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. 2-GEMMASCOPE-RES-16K
    11. 12953
    Prev
    Next
    INDEX
    Explanations

    written notations or markers related to bold mathematical variables or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Whelan
    -0.56
    webElementGuid
    -0.54
     Stamm
    -0.50
    ymce
    -0.48
    wapV
    -0.48
     Lombardo
    -0.47
     Sosa
    -0.47
    htbp
    -0.47
    -------
    -0.46
     Shaft
    -0.46
    POSITIVE LOGITS
    bf
    0.70
    Albert
    0.66
     Albert
    0.62
    Algebra
    0.60
     ALBERT
    0.60
    новништво
    0.57
    chalk
    0.55
    albert
    0.55
     bf
    0.55
    Chemistry
    0.55
    Activations Density 0.453%

    No Known Activations