© 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. 15-GEMMASCOPE-RES-16K
    11. 3592
    Prev
    Next
    INDEX
    Explanations

    text that discusses legal terms and concepts, particularly relating to arguments and interpretations in a legal context

    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
     ainfi
    -0.82
     feroit
    -0.82
     vôtre
    -0.79
     pouvoit
    -0.78
     giù
    -0.78
     nuages
    -0.78
     scattata
    -0.77
    enderror
    -0.74
     auroit
    -0.73
     Diretto
    -0.73
    POSITIVE LOGITS
     been
    0.69
     experience
    0.62
     access
    0.61
     had
    0.57
     nodig
    0.56
     k
    0.52
     ten
    0.51
     
    0.51
     problem
    0.47
    ten
    0.46
    Activations Density 0.493%

    No Known Activations