© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3118
    Prev
    Next
    INDEX
    Explanations

    code-related constructs, particularly those involving data structures and algorithms

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    C++ smart pointer declarations and template syntax (std::unique_ptr, std::shared_ptr with angle brackets).

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    addContainerGap
    -0.32
    BeforeClass
    -0.28
     telas
    -0.28
    RestTemplate
    -0.27
    Geografía
    -0.26
    Persön
    -0.26
     siglos
    -0.25
     tensión
    -0.25
    ศ
    -0.25
    INLINE
    -0.24
    POSITIVE LOGITS
     vector
    0.90
    vector
    0.78
     vectors
    0.77
     vec
    0.75
     Vectors
    0.71
     ویکی‌پدی
    0.69
     vecteur
    0.69
    WithIOException
    0.68
    ﮗ
    0.68
     вектор
    0.67
    Activations Density 0.427%

    No Known Activations