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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7153
    Prev
    Next
    INDEX
    Explanations

    elements related to legal or financial compliance, particularly regarding tax matters

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

    IRS, tax, and returns

    np_acts-logits-general · gemini-2.0-flash

    tax returns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    EndInit
    -0.79
     للاسماء
    -0.76
     <=",
    -0.71
    BeginInit
    -0.71
    WebVitals
    -0.70
    posedge
    -0.70
    ArgsConstructor
    -0.69
    HtmlAttribute
    -0.65
    MemoryWarning
    -0.63
    awtextra
    -0.63
    POSITIVE LOGITS
     tax
    1.85
     Tax
    1.73
    Tax
    1.60
    tax
    1.50
     TAX
    1.41
    TAX
    1.33
     taxation
    1.25
     taxpayers
    1.24
     IRS
    1.23
     taxpayer
    1.23
    Activations Density 0.391%

    No Known Activations