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. 9-GEMMASCOPE-RES-16K
    6. 3786
    Prev
    Next
    INDEX
    Explanations

    references to political titles, specifically mayors and governors

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

    Titles: "Governor" or "Mayor"

    np_acts-logits-general · gemini-2.0-flash

    political office titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GraphicsUnit
    -0.56
    styleType
    -0.53
     kasarigan
    -0.51
     CascadeType
    -0.49
    ArgsConstructor
    -0.48
    IsContent
    -0.47
     nonUne
    -0.47
    enderror
    -0.45
    ptid
    -0.44
     createSprite
    -0.43
    POSITIVE LOGITS
     Governor
    1.54
     governor
    1.52
    Governor
    1.44
     GOVERNOR
    1.30
     Mayor
    1.28
     governors
    1.24
    governor
    1.21
     mayor
    1.17
     Governors
    1.16
    Mayor
    1.16
    Activations Density 0.228%

    No Known Activations