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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2170
    Prev
    Next
    INDEX
    Explanations

    identifiers and variables related to programming or code operations

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

    Variables, often single letters

    np_acts-logits-general · gemini-2.0-flash

    code snippets and programming terms

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    "],
    
    -0.82
    "},
    
    -0.76
    )++;
    -0.71
    "}>
    -0.71
    ++
    
    -0.70
    [];
    
    -0.69
    "]="
    -0.65
    "){
    
    -0.65
    "]);
    
    -0.64
    !")
    
    -0.63
    POSITIVE LOGITS
     olev
    0.59
     estekak
    0.56
     others
    0.56
     فريبيس
    0.54
     незавершена
    0.54
     Dès
    0.53
    createNewFile
    0.49
    Collegamenti
    0.49
     =
    0.48
    reportWebVitals
    0.48
    Activations Density 0.089%

    No Known Activations