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. 5-GEMMASCOPE-RES-16K
    6. 4925
    Prev
    Next
    INDEX
    Explanations

    terms associated with civilians and their interactions with the government and private sector

    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
    hematical
    -0.63
    IsContent
    -0.63
    odule
    -0.61
     Catt
    -0.60
     equalization
    -0.58
     automatiques
    -0.57
     oriental
    -0.56
    wareness
    -0.56
    degard
    -0.56
     الحره
    -0.55
    POSITIVE LOGITS
     civilian
    1.03
     Civilian
    0.86
     civilians
    0.81
    民間
    0.78
     civile
    0.74
     private
    0.68
     civiles
    0.66
     vrijwilli
    0.64
     privata
    0.60
    private
    0.58
    Activations Density 0.553%

    No Known Activations