Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1637
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to financial responsibilities and obligations

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

    Payment or obligation to pay

    np_acts-logits-general · gemini-2.0-flash

    pay or paying

    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
     Jefus
    -0.64
     poffe
    -0.63
     BoxDecoration
    -0.60
    Einzelnachweise
    -0.59
    calaureate
    -0.57
     poffible
    -0.55
    IUrlHelper
    -0.54
    ]")]
    -0.54
     againſt
    -0.54
     purpoſe
    -0.54
    POSITIVE LOGITS
     paying
    2.17
     pay
    1.93
     Paying
    1.86
    Paying
    1.83
    paying
    1.82
     pays
    1.81
     paid
    1.79
    pay
    1.65
     PAY
    1.64
     Pay
    1.60
    Activations Density 0.313%

    No Known Activations