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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 6741
    Prev
    Next
    INDEX
    Explanations

    references to the United States and its locales

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

    mentions of locations in the USA

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     potential
    -0.75
    ly
    -0.74
    ness
    -0.73
    ه‌
    -0.71
    o
    -0.69
    p
    -0.69
    ...
    -0.67
    <eos>
    -0.66
    ')
    -0.65
    ch
    -0.64
    POSITIVE LOGITS
     USA
    1.53
    USA
    1.47
     usa
    1.01
     للاسماء
    1.00
     Usa
    0.97
     spalle
    0.88
    nologies
    0.83
     contextLoads
    0.82
     myſelf
    0.81
    RTLD
    0.81
    Activations Density 0.079%

    No Known Activations