© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 652
    Prev
    Next
    INDEX
    Explanations

    references to threading and concurrency errors

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

    references to threading and associated exceptions in programming

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

    exception and syndication

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     typelib
    -0.63
    DockStyle
    -0.58
    EndGlobalSection
    -0.55
     égard
    -0.51
    mybatisplus
    -0.50
     costruire
    -0.49
    side
    -0.48
     rağmen
    -0.47
    AndEndTag
    -0.46
     navigu
    -0.45
    POSITIVE LOGITS
    ruptedException
    0.64
     مرئيه
    0.63
    ")));
    
    0.61
     Савезне
    0.61
     THREAD
    0.61
     sī
    0.59
    RenderAtEndOf
    0.59
     Thread
    0.58
    ".
    
    0.58
    testens
    0.57
    Activations Density 0.005%

    No Known Activations