© 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. 2-GEMMASCOPE-RES-16K
    11. 9103
    Prev
    Next
    INDEX
    Explanations

    mentions of the Roman Empire or historical references related to Rome

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Medal
    -0.76
     hâte
    -0.71
    Medal
    -0.69
     vertes
    -0.69
     medal
    -0.69
     honnête
    -0.68
     polaire
    -0.67
     déchir
    -0.67
    medal
    -0.65
     impré
    -0.63
    POSITIVE LOGITS
     Roman
    0.88
     tanks
    0.82
     tank
    0.78
    Roman
    0.72
     shells
    0.70
     Tank
    0.69
     immun
    0.68
     Tanks
    0.67
     Shell
    0.67
    UIControlState
    0.65
    Activations Density 0.043%

    No Known Activations