© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 62156
    Prev
    Next
    INDEX
    Explanations

    references to the mathematical concept of sine, particularly in various forms like sine functions and sine waves

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Sinful, Sinister, Sinus, Sinfunction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    they
    -0.47
    ️
    -0.45
     niitä
    -0.45
     Jerzy
    -0.45
    berger
    -0.44
     asemenea
    -0.44
     امريكا
    -0.43
    adera
    -0.43
    dyti
    -0.43
    BERGER
    -0.43
    POSITIVE LOGITS
     Sin
    2.13
    Sin
    2.09
     sin
    2.02
    sin
    1.84
     SIN
    1.76
    SIN
    1.60
     Sinclair
    1.37
     sins
    1.14
     Sinus
    1.09
     Sinha
    1.09
    Activations Density 0.014%

    No Known Activations