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. 10312
    Prev
    Next
    INDEX
    Explanations

    programming-related conditional statements and checks

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

    Conditionals checking object type using `is`

    np_acts-logits-general · gemini-2.0-flash

    is followed by method calls

    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
    참고
    -0.62
    DotNetBar
    -0.54
    jsonPath
    -0.54
    ajan
    -0.53
     may
    -0.52
     مشين
    -0.49
    hibernate
    -0.48
     taip
    -0.46
    doria
    -0.45
    writeHead
    -0.45
    POSITIVE LOGITS
     alguno
    0.67
    SharedDtor
    0.67
    enough
    0.65
     sufficiently
    0.65
    ?')
    0.64
     genoux
    0.64
     enough
    0.64
    ?
    
    0.63
     alguna
    0.62
    的話
    0.62
    Activations Density 0.217%

    No Known Activations