Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 6860
    Prev
    Next
    INDEX
    Explanations

    information related to political figures, their backgrounds, and careers

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

    Guyana, Barbados, Jamaica, Caribbean

    np_acts-logits-general · gemini-2.0-flash

    Windsor Park

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initComponents
    -0.74
    rizona
    -0.73
     OREGON
    -0.69
    GEBURTSDATUM
    -0.67
    QMetaType
    -0.66
     vapors
    -0.65
     defaultstate
    -0.65
     Plano
    -0.65
     neurom
    -0.64
     Butte
    -0.63
    POSITIVE LOGITS
     Barbados
    0.96
     Jamaica
    0.96
     Caribbean
    0.93
     Guyana
    0.86
    ieteur
    0.83
    Jamaica
    0.81
    Barbados
    0.81
     Jamaican
    0.81
    Kaieteur
    0.78
    Caribbean
    0.78
    Activations Density 0.089%

    No Known Activations