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

    Neuronpedia

    APICircuit 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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 846
    Prev
    Next
    INDEX
    Explanations

    references to locations and institutions related to the legal or correctional system

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

    references to official entities, specifically government departments and locations related to Maine

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

    county jail locations

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     idéal
    -0.52
    Filmografie
    -0.52
     mutiny
    -0.51
     Gauteng
    -0.51
     Huerta
    -0.49
     Haryana
    -0.48
    fxml
    -0.48
     Fullerton
    -0.47
     Hales
    -0.46
     Mut
    -0.46
    POSITIVE LOGITS
     Maine
    1.26
    Maine
    1.13
     maine
    0.96
     Bangor
    0.90
    oredCriteria
    0.79
    DockStyle
    0.71
     lobster
    0.70
     Quod
    0.69
    الحياه
    0.69
     Portland
    0.69
    Activations Density 0.082%

    No Known Activations