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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 13913
    Prev
    Next
    INDEX
    Explanations

    references to judicial processes and court rulings

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

    "Of" followed by a county name

    np_acts-logits-general · gemini-2.0-flash

    names of counties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BOSTON
    -0.52
    adalajara
    -0.51
     chilena
    -0.51
     Nagoya
    -0.50
    äiv
    -0.50
     pylori
    -0.48
    haikusbot
    -0.47
     alimentaria
    -0.47
    endmodule
    -0.47
     espont
    -0.45
    POSITIVE LOGITS
     counties
    0.94
     county
    0.81
     Montgomery
    0.79
     Counties
    0.79
     COUNT
    0.71
     County
    0.69
     Cook
    0.66
     Jefferson
    0.65
     Weld
    0.65
    IntoConstraints
    0.64
    Activations Density 0.361%

    No Known Activations