© 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. 25-GEMMASCOPE-RES-16K
    11. 118
    Prev
    Next
    INDEX
    Explanations

    references to locations and structures in Florida, particularly national cemeteries and related administrative details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mongolian
    -0.89
    Sask
    -0.73
     Mongolia
    -0.70
     Punjabi
    -0.70
     Saskatoon
    -0.69
     Lesotho
    -0.68
     ModelExpression
    -0.68
     Sichuan
    -0.66
     Sikkim
    -0.65
     Alder
    -0.65
    POSITIVE LOGITS
     Florida
    2.22
    Florida
    2.05
     FLORIDA
    1.89
     florida
    1.68
    florida
    1.62
    FLOR
    1.59
     Flor
    1.58
     Tallahassee
    1.58
     Tampa
    1.58
     Broward
    1.52
    Activations Density 0.534%

    No Known Activations