© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 10579
    Prev
    Next
    INDEX
    Explanations

    keywords related to legal or legislative matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tonight
    -1.14
     tomorrow
    -1.02
     demain
    -0.92
     todays
    -0.89
    tomorrow
    -0.87
     amanhã
    -0.85
    rungsseite
    -0.85
     today
    -0.85
     Currently
    -0.84
    来週
    -0.83
    POSITIVE LOGITS
     damals
    1.00
    当时的
    1.00
    當時
    0.98
    当时
    0.95
    当時は
    0.92
    那时候
    0.90
     тогда
    0.84
     damaligen
    0.81
     wtedy
    0.80
    当時
    0.77
    Activations Density 0.546%

    No Known Activations