© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 882
    Prev
    Next
    INDEX
    Explanations

    terms related to Greek mythology

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

    ancient Greece

    np_acts-logits-general · gemini-2.0-flash

    greek language and culture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ัญ
    -0.37
     Jesu
    -0.36
     ακό
    -0.36
     tác
    -0.35
    ocardium
    -0.35
    Jes
    -0.35
     ακόμα
    -0.34
     trans
    -0.33
    eml
    -0.33
    ul
    -0.32
    POSITIVE LOGITS
     Greek
    1.31
     Greece
    1.28
     GREEK
    1.20
     greek
    1.17
    Greek
    1.16
     Athens
    1.16
     grecque
    1.16
    Greece
    1.13
     Hellenic
    1.11
     griego
    1.09
    Activations Density 0.103%

    No Known Activations