© 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. 9651
    Prev
    Next
    INDEX
    Explanations

    references to historical and cultural heritage

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

    Ancient or historic topics

    np_acts-logits-general · gemini-2.0-flash

    ancient history and civilizations

    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
    Personensuche
    -0.51
     allAfrica
    -0.44
    hatsu
    -0.43
     corrig
    -0.42
     CreateTagHelper
    -0.42
     <=",
    -0.41
    kháu
    -0.41
    Refresh
    -0.41
     Bambi
    -0.40
     gelatina
    -0.40
    POSITIVE LOGITS
     ancient
    1.32
     Ancient
    1.21
    ancient
    1.19
    Ancient
    1.16
     archaeological
    1.13
     archeological
    1.09
     historic
    1.05
     antiquity
    0.99
     antique
    0.99
    Archae
    0.99
    Activations Density 0.253%

    No Known Activations