© 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. 18-GEMMASCOPE-RES-16K
    11. 6964
    Prev
    Next
    INDEX
    Explanations

    references to academic studies and approvals

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

    Abbreviations such as Nl, CH, UK, DE, IT and RU

    np_acts-logits-general · gemini-2.0-flash

    NWO via Spinoza Prize, Aernout Mik (Nl)

    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
     mijne
    -1.02
     zijne
    -0.95
     gezet
    -0.83
     dezelve
    -0.79
     goederen
    -0.77
    ljiv
    -0.74
     apparaat
    -0.74
     vergeten
    -0.73
     muur
    -0.73
     wikipagina
    -0.71
    POSITIVE LOGITS
     defaultstate
    0.65
     webshop
    0.60
     transpar
    0.60
    Beschrijving
    0.60
     natu
    0.60
    soort
    0.60
    Aantal
    0.58
    IsContent
    0.57
     enthousi
    0.56
     Catawiki
    0.55
    Activations Density 0.188%

    No Known Activations