© 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. 22-GEMMASCOPE-RES-16K
    11. 8097
    Prev
    Next
    INDEX
    Explanations

    references to Cuban political figures and events

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

    Cuba

    np_acts-logits-general · gemini-2.0-flash

    Cuba, Cuban nationality, and related entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seattle
    -0.77
    Seattle
    -0.76
     Kannada
    -0.76
    seattle
    -0.75
    (!__
    -0.63
     Tacoma
    -0.62
     chileno
    -0.62
     chilen
    -0.62
    Oregon
    -0.60
     mexicanos
    -0.60
    POSITIVE LOGITS
     Cuba
    1.54
     Cuban
    1.43
     Havana
    1.39
    Cuba
    1.38
     Cubans
    1.22
    Cuban
    1.22
     cubanos
    1.20
    Cub
    1.19
     cuba
    1.16
     Cub
    1.13
    Activations Density 0.093%

    No Known Activations