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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53039
    Prev
    Next
    INDEX
    Explanations

    references to fiscal years and budget allocations

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

    fiscal year and FY designations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnchorStyles
    -0.91
    MENAFN
    -0.84
     BoxDecoration
    -0.83
    IntoConstraints
    -0.82
    MessageTagHelper
    -0.80
    #+#
    -0.77
     InputDecoration
    -0.74
    GOTREF
    -0.71
     chi̍t
    -0.68
     שוליים
    -0.68
    POSITIVE LOGITS
     FY
    0.77
     fiscal
    0.75
    FY
    0.63
     Fiscal
    0.62
    fiscal
    0.61
     FISCAL
    0.57
    nimo
    0.55
     budget
    0.54
     Fy
    0.54
     budgets
    0.52
    Activations Density 0.023%

    No Known Activations