Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 1466
    Prev
    Next
    INDEX
    Explanations

    instances of legal and judicial terminology, particularly in the context of court decisions and proceedings

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

    California, Calif, Cal

    np_acts-logits-general · gemini-2.0-flash

    California legal and official mentions

    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
    Skocz
    -0.79
     utafitiHapana
    -0.57
     ProtoMessage
    -0.57
    Przypisy
    -0.56
     tornado
    -0.56
     phospho
    -0.55
     StatefulWidget
    -0.54
    ioterapia
    -0.53
     <<<<<<<<<<<<<<
    -0.53
     VIDEOTAPE
    -0.53
    POSITIVE LOGITS
     California
    1.47
     CALIFORNIA
    1.40
    California
    1.38
     Califor
    1.36
     Sacramento
    1.32
     Californian
    1.29
     Californie
    1.25
     Calif
    1.23
    CALIFORNIA
    1.22
     CALIFORN
    1.20
    Activations Density 0.547%

    No Known Activations