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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 11039
    Prev
    Next
    INDEX
    Explanations

    references to empires and imperial authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    JAV
    -0.63
    Wit
    -0.60
    ear
    -0.59
     Bot
    -0.57
     Daryl
    -0.54
     Thom
    -0.54
     Greenway
    -0.53
     jav
    -0.53
     gat
    -0.53
    elen
    -0.53
    POSITIVE LOGITS
     Empire
    2.90
    Empire
    2.69
     empire
    2.54
     EMPIRE
    2.46
    empire
    2.22
     empires
    2.16
     Empires
    1.97
     Imperial
    1.89
     imperial
    1.86
    Imperial
    1.78
    Activations Density 0.065%

    No Known Activations