© 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. 11-GEMMASCOPE-RES-16K
    11. 8558
    Prev
    Next
    INDEX
    Explanations

    elements related to complex relationships and interactions among various factors or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    package
    -0.31
    nodeList
    -0.31
     must
    -0.29
     en
    -0.26
     duquel
    -0.26
    nost
    -0.26
     banques
    -0.26
     present
    -0.25
     intégré
    -0.25
    มาก
    -0.24
    POSITIVE LOGITS
     ویکی‌پدی
    0.79
     snippetHide
    0.77
    writeFieldEnd
    0.76
     Chwiliwch
    0.72
    RegressionTest
    0.69
    Autoritní
    0.68
    ंदीखरीदारी
    0.68
    UnitTesting
    0.63
    MENAFN
    0.63
    XtraReports
    0.62
    Activations Density 2.183%

    No Known Activations