Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 33-GEMMASCOPE-RES-131K
    6. 65864
    Prev
    Next
    INDEX
    Explanations

    programming terminology and code structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.57
    /**
    -0.54
    ollectionView
    -0.54
    SourceChecksum
    -0.54
    ReusableCell
    -0.52
    PagerAdapter
    -0.50
     ویکی‌پدی
    -0.50
    ynb
    -0.50
     StatelessWidget
    -0.50
     MainAxisSize
    -0.49
    POSITIVE LOGITS
     expect
    0.44
     envíos
    0.37
     EconPapers
    0.37
    expect
    0.35
    响应
    0.35
     vyb
    0.34
     Expect
    0.33
     test
    0.33
     muñeco
    0.33
     response
    0.33
    Activations Density 0.002%

    No Known Activations