© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 3675
    Prev
    Next
    INDEX
    Explanations

    instances of the term "ruling" and its variations related to court decisions and legal outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gainera
    -0.61
     Redondo
    -0.57
     InputDecoration
    -0.57
    textLabel
    -0.56
    ostom
    -0.55
     brut
    -0.54
    badi
    -0.54
     QD
    -0.51
    PasswordEncoder
    -0.50
     Roque
    -0.50
    POSITIVE LOGITS
     ruling
    1.36
     Ruling
    1.33
    ruling
    1.21
     ruled
    1.15
     Francis
    1.02
    Francis
    0.95
    ruled
    0.92
     Ru
    0.86
     rulings
    0.84
     FRANCIS
    0.73
    Activations Density 0.094%

    No Known Activations