© 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. 2-GEMMASCOPE-RES-16K
    11. 16336
    Prev
    Next
    INDEX
    Explanations

    occurrences of class and interface keywords in a coding context

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    KommentareTeilen
    -0.69
    SBATCH
    -0.57
    wapV
    -0.54
    تقاوى
    -0.50
    ########.
    -0.47
    IndentedString
    -0.47
    IUrlHelper
    -0.46
    ArrowToggle
    -0.45
     utafitiHapana
    -0.45
     Италијани
    -0.44
    POSITIVE LOGITS
     class
    2.38
    class
    2.02
     classes
    1.68
     classe
    1.61
     clase
    1.52
    classes
    1.49
     Class
    1.45
     CLASS
    1.38
    Class
    1.36
     Classes
    1.34
    Activations Density 0.079%

    No Known Activations