© 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. 28-GEMMASCOPE-RES-16K
    11. 7832
    Prev
    Next
    INDEX
    Explanations

    programming-related classes and methods, particularly those associated with game mechanics and data handling

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

    The token "class" or words containing "class"

    np_acts-logits-general · gemini-2.0-flash

    programming class references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esternos
    -0.59
     compliance
    -0.54
    :✨
    -0.50
     wireType
    -0.49
     Италијани
    -0.49
    lapsingToolbar
    -0.46
    DockStyle
    -0.44
    Compliance
    -0.43
    compliance
    -0.42
     comply
    -0.41
    POSITIVE LOGITS
    class
    1.04
     class
    0.98
    getClass
    0.71
     classe
    0.70
     clase
    0.66
     Class
    0.65
     getClass
    0.62
     classes
    0.61
     nahilalakip
    0.57
     klasse
    0.56
    Activations Density 0.127%

    No Known Activations