© 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. 3-GEMMASCOPE-RES-16K
    11. 10630
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and procedural actions related to bail and custody

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nghề
    -0.58
    rece
    -0.56
     ricca
    -0.56
     classiques
    -0.52
     montré
    -0.51
     composés
    -0.50
     articoli
    -0.50
     rimasto
    -0.49
     stä
    -0.48
     pilas
    -0.47
    POSITIVE LOGITS
     surla
    1.22
     Speaking
    1.21
    Speaking
    1.18
     speaking
    0.99
    ValueStyle
    0.93
    StoryboardSegue
    0.90
     inflater
    0.88
     GenerationType
    0.86
    speaking
    0.85
     становника
    0.84
    Activations Density 0.802%

    No Known Activations