© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 55203
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and expressions related to derivatives

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

    calculating mathematical derivatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     ब्रेकडाउन
    -0.85
     للمعارف
    -0.68
     للاسماء
    -0.68
     kaarangay
    -0.66
     ostavi
    -0.64
     HttpNotFound
    -0.64
     الحره
    -0.62
    rungsseite
    -0.62
     ویکی‌پدی
    -0.62
    complexContent
    -0.61
    POSITIVE LOGITS
     derivative
    0.51
    Derivative
    0.50
    derivative
    0.47
     analysis
    0.40
    grad
    0.40
    nabla
    0.40
    Autowired
    0.39
     Sonntag
    0.37
     derivatives
    0.35
     Derivative
    0.35
    Activations Density 0.237%

    No Known Activations