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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6860
    Prev
    Next
    INDEX
    Explanations

    references to ancient Greek mythology and culture

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

    Ancient Roman or Greek history/mythology

    np_acts-logits-general · gemini-2.0-flash

    ancient Greek Roman history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.75
    Hochspringen
    -0.71
    tamount
    -0.58
     typelib
    -0.57
     متعلقه
    -0.56
    EndInit
    -0.56
    ButtonItem
    -0.54
     Serializable
    -0.54
     betweenstory
    -0.54
     uruguay
    -0.53
    POSITIVE LOGITS
     ancient
    1.34
     Ancient
    1.30
    ancient
    1.23
    Ancient
    1.22
     Roman
    1.22
     Greek
    1.21
     antiquity
    1.13
     classical
    1.06
     Classical
    1.05
    Greek
    1.02
    Activations Density 0.183%

    No Known Activations