© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 7379
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal challenges and dispute resolutions

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

    Follows "the", "of", or "sufficiency"

    np_acts-logits-general · gemini-2.0-flash

    challenge claims and sufficiency

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.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
     Iro
    -0.56
     Tener
    -0.56
     threads
    -0.54
     kindred
    -0.54
    /*
    -0.54
     bris
    -0.53
     Vikipedi
    -0.52
     Kend
    -0.52
     loom
    -0.50
     Fins
    -0.50
    POSITIVE LOGITS
     assertion
    0.67
     assertions
    0.66
     claims
    0.65
     claim
    0.64
     claimed
    0.64
    TabIndex
    0.63
     ویکی‌پدیا
    0.63
    帖最后由
    0.62
    EventQueue
    0.59
     aveug
    0.59
    Activations Density 0.708%

    No Known Activations