© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 187
    Prev
    Next
    INDEX
    Explanations

    references to the dollar and its various forms

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

    currency, especially US dollars

    np_acts-logits-general · gemini-2.0-flash

    dollar or percent

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    揄
    -0.41
     Taktlose
    -0.37
     Rab
    -0.35
     &
    -0.33
     AI
    -0.33
     staged
    -0.33
     مخ
    -0.32
     San
    -0.32
     W
    -0.32
     VI
    -0.32
    POSITIVE LOGITS
     dollars
    1.27
     dollar
    1.19
    dollars
    1.13
     DOLLARS
    1.13
     Dollar
    1.09
     Dollars
    1.06
    Dollar
    1.03
    dollar
    1.02
     centimeters
    0.96
     centimeter
    0.96
    Activations Density 0.327%

    No Known Activations