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. 10914
    Prev
    Next
    INDEX
    Explanations

    blocks of code related to error handling and thread management in programming

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

    Likely within try/catch blocks

    np_acts-logits-general · gemini-2.0-flash

    try blocks

    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
    ----</
    -0.65
    ("")]
    
    -0.64
     nakalista
    -0.63
    __;
    -0.63
    EDEFAULT
    -0.62
    беріга
    -0.61
     تضيفلها
    -0.58
     dataSnapshot
    -0.56
     surla
    -0.55
    rrggbb
    -0.54
    POSITIVE LOGITS
    المناصب
    0.61
    UIManager
    0.61
     useStyles
    0.50
     hood
    0.49
     ***!
    0.47
    nthetic
    0.46
    TestingModule
    0.46
    andere
    0.46
    المشاركات
    0.46
    INDER
    0.45
    Activations Density 0.030%

    No Known Activations