© 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. 22-GEMMASCOPE-RES-16K
    11. 924
    Prev
    Next
    INDEX
    Explanations

    financial terms related to loans and repayments

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

    paying

    np_acts-logits-general · gemini-2.0-flash

    payment and arrears

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     وتسجيلات
    -0.62
     Bened
    -0.58
    Clik
    -0.49
    存于互联网档案馆
    -0.49
    UnusedPrivate
    -0.49
    openzeppelin
    -0.48
    Legături
    -0.47
     Verw
    -0.47
     maroc
    -0.46
    setLevel
    -0.46
    POSITIVE LOGITS
     payment
    2.89
     paying
    2.84
     pay
    2.72
     paid
    2.71
     Paying
    2.58
    paying
    2.53
     pays
    2.50
    Paying
    2.49
    payment
    2.47
     payments
    2.46
    Activations Density 0.279%

    No Known Activations