© 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. 31-GEMMASCOPE-RES-16K
    11. 7791
    Prev
    Next
    INDEX
    Explanations

    expressions related to object-oriented programming constructs, such as classes, methods, and object relationships

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

    class type references and object instantiation patterns in code.

    oai_token-act-pair · claude-4-5-haikuTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    Tembelea
    -0.41
    뀜
    -0.34
     التس
    -0.33
    GLint
    -0.33
     mand
    -0.33
     darauf
    -0.33
    ⓧ
    -0.33
     tru
    -0.33
    ANDUM
    -0.33
     dudas
    -0.32
    POSITIVE LOGITS
    class
    0.92
     class
    0.89
     getClass
    0.84
     classe
    0.81
     classes
    0.74
     clase
    0.72
    getClass
    0.70
     clazz
    0.68
     Class
    0.67
    setClass
    0.67
    Activations Density 0.233%

    No Known Activations