© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9026
    Prev
    Next
    INDEX
    Explanations

    specific code comments and structure in programming documents

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

    closing comment delimiters in source 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
     تكبرها
    -0.45
    principalTable
    -0.41
    contentLoaded
    -0.39
    Viitteet
    -0.34
    льності
    -0.34
    FUNCTIONS
    -0.34
    aimerais
    -0.33
    ografija
    -0.33
    تقاوى
    -0.31
     skr
    -0.31
    POSITIVE LOGITS
    import
    1.01
     import
    0.79
    Import
    0.60
    出版年
    0.57
     Import
    0.56
     IMPORT
    0.54
    documentclass
    0.53
    setupUi
    0.53
     importar
    0.53
     importa
    0.52
    Activations Density 0.209%

    No Known Activations