© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 4771
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "try" in various contexts

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

    Code snippets containing "try"

    np_acts-logits-general · gemini-2.0-flash

    try code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addCriterion
    -0.78
     للمعارف
    -0.72
     Мексичка
    -0.68
    glVertex
    -0.68
     فريبيس
    -0.68
    Vidite
    -0.65
    + 
    -0.64
    NameInMap
    -0.63
     />';
    -0.61
    jsxFileName
    -0.61
    POSITIVE LOGITS
     الحره
    0.64
    try
    0.63
    帖最后由
    0.62
    findpost
    0.50
     سكانية
    0.50
    {
    0.48
    yntaxException
    0.46
     larmes
    0.45
    Numerology
    0.44
     bilingual
    0.44
    Activations Density 0.016%

    No Known Activations