© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 3665
    Prev
    Next
    INDEX
    Explanations

    instances of programming function definitions and variable assignments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.62
    ADVERTISEMENT
    -0.58
    LEncoder
    -0.58
    __':
    -0.55
     NIS
    -0.54
    تمبر
    -0.53
     ActionResult
    -0.52
    enderror
    -0.52
    __':
    -0.52
     BufferedWriter
    -0.51
    POSITIVE LOGITS
    EndGlobalSection
    0.53
    τέλε
    0.49
    ValueStyle
    0.49
     transfieras
    0.48
     виправивши
    0.47
     Satu
    0.46
     ویکی‌پدیا
    0.45
    __(/*!
    0.45
    utsches
    0.44
     بيها
    0.43
    Activations Density 0.028%

    No Known Activations