© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1650
    Prev
    Next
    INDEX
    Explanations

    references to governmental and county-related entities and officials

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

    "County" or "Counties"

    np_acts-logits-general · gemini-2.0-flash

    county government and officials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     frost
    -0.65
    PreferredItem
    -0.56
    IEE
    -0.54
    ftes
    -0.53
    аз
    -0.52
     GenerationType
    -0.52
    gment
    -0.51
    romptu
    -0.50
    adze
    -0.50
    GMENT
    -0.50
    POSITIVE LOGITS
     County
    1.80
     county
    1.68
    County
    1.55
     COUNTY
    1.54
    county
    1.53
    COUNTY
    1.39
     counties
    1.23
     Sheriff
    1.09
    Sheriff
    1.08
     Counties
    1.06
    Activations Density 0.135%

    No Known Activations