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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11951
    Prev
    Next
    INDEX
    Explanations

    legal terminology and phrases related to court rulings and proceedings

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

    Preceding words of legal terms

    np_acts-logits-general · gemini-2.0-flash

    the Court or law

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    TemporalType
    -0.73
     gyhoeddwyd
    -0.71
     Résultat
    -0.70
     विश्वसनीयता
    -0.70
     famously
    -0.68
     Celui
    -0.67
     CreateTagHelper
    -0.65
     chemists
    -0.64
     fameux
    -0.63
     critters
    -0.61
    POSITIVE LOGITS
     foregoing
    0.94
     provisions
    0.86
     above
    0.77
     present
    0.66
     purpose
    0.63
    原始内容存档于
    0.61
     said
    0.61
     Authority
    0.61
     following
    0.60
    以上
    0.59
    Activations Density 0.979%

    No Known Activations