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-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15666
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations, especially in Tennessee

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

    Nashville or Tennessee

    np_acts-logits-general · gemini-2.0-flash

    Nashville, Tennessee

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    QMetaType
    -0.46
     Wikimedijinoj
    -0.45
    #
    -0.40
     dAtA
    -0.38
    <!--[
    -0.36
    FXMLLoader
    -0.36
     RoutedEventArgs
    -0.35
    oa̍t
    -0.34
    Rhestr
    -0.34
     nonUne
    -0.34
    POSITIVE LOGITS
     Nashville
    1.32
    Nashville
    1.21
     Tennessee
    1.11
    Tennessee
    1.01
     Tenn
    1.01
     Vanderbilt
    0.83
     nash
    0.81
     TN
    0.80
    nash
    0.77
    NESSEE
    0.75
    Activations Density 0.086%

    No Known Activations