© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 83692
    Prev
    Next
    INDEX
    Explanations

    references to system control functions and libraries in programming

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

    system calls and libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jazdu
    -0.38
    jej
    -0.33
    期刊论文
    -0.33
    Portail
    -0.33
    TextAlignment
    -0.32
    MMdd
    -0.32
     قرب
    -0.32
     /\.(
    -0.32
     Eub
    -0.32
     aanbod
    -0.32
    POSITIVE LOGITS
     PyQt
    1.29
    BeginInit
    0.86
    出版年
    0.84
    QMessageBox
    0.72
    fcntl
    0.69
    ToTensor
    0.67
    bitset
    0.66
    httphttps
    0.66
    Datuak
    0.63
    Geplaatst
    0.62
    Activations Density 0.001%

    No Known Activations