© 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. 9-GEMMASCOPE-RES-16K
    11. 11382
    Prev
    Next
    INDEX
    Explanations

    programming-related terminology, specifically related to LLVM and code structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Vermögen
    -0.36
     ritratto
    -0.35
     dokumenta
    -0.33
     bénévol
    -0.32
     bicchiere
    -0.31
     palabra
    -0.31
    vermögen
    -0.31
     quenched
    -0.31
    ClientSize
    -0.31
    ilangkan
    -0.31
    POSITIVE LOGITS
    AuxInt
    0.79
     ویکی‌پدیا
    0.54
     незавершена
    0.54
    verifyException
    0.53
    AddArg
    0.52
     surla
    0.52
    AxisAlignment
    0.51
    ceps
    0.50
    IVEREF
    0.50
    PerformLayout
    0.50
    Activations Density 0.678%

    No Known Activations