© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 16163
    Prev
    Next
    INDEX
    Explanations

    references to taxes and taxation-related topics

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

    the word "tax" in various contexts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    办
    -0.38
    ism
    -0.36
    ismi
    -0.33
    lease
    -0.33
     اص
    -0.33
    isms
    -0.33
     вен
    -0.32
     tạp
    -0.32
     giá
    -0.32
     asupra
    -0.31
    POSITIVE LOGITS
     paid
    0.72
     charged
    0.71
     payable
    0.70
     المعيارى
    0.67
     levied
    0.66
     payed
    0.65
     Вікі
    0.64
     متعلقه
    0.64
    MemoryWarning
    0.63
    paid
    0.60
    Activations Density 0.272%

    No Known Activations