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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 268
    Prev
    Next
    INDEX
    Explanations

    terms related to tax relief and exemptions

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

    Exclusion, exemption, or relief from penalty/liability

    np_acts-logits-general · gemini-2.0-flash

    exemption from penalties or obligations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     calculées
    -0.38
    原始内容存档
    -0.38
     hamsters
    -0.35
     calcul
    -0.35
    EFIAPI
    -0.34
     thirsty
    -0.34
    éraire
    -0.34
     hik
    -0.34
     hår
    -0.34
    kwür
    -0.33
    POSITIVE LOGITS
    ंदीखरीदारी
    0.64
     exemption
    0.60
    ChildScrollView
    0.57
     Exemption
    0.55
     betweenstory
    0.55
     miễn
    0.54
    gnore
    0.54
     exempted
    0.53
    تقاوى
    0.52
     excused
    0.52
    Activations Density 0.388%

    No Known Activations