© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 10408
    Prev
    Next
    INDEX
    Explanations

    LaTeX formatting elements, particularly those associated with mathematical expressions

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

    Bracketed expressions, often with symbols or math

    np_acts-logits-general · gemini-2.0-flash

    math and science references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.67
     незавершена
    -0.57
    mergeFrom
    -0.56
    Зміст
    -0.56
    Hozzáférés
    -0.54
    akim
    -0.53
    levance
    -0.53
    $​
    -0.51
    rungsseite
    -0.50
     الوطنيه
    -0.50
    POSITIVE LOGITS
     cohomology
    0.60
     Enclosed
    0.53
     архивлан
    0.51
     schla
    0.51
     Avignon
    0.50
     Solu
    0.49
     Piccadilly
    0.48
     Sonya
    0.48
    ั้ง
    0.48
    PageContext
    0.48
    Activations Density 0.035%

    No Known Activations