© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 862
    Prev
    Next
    INDEX
    Explanations

    the start of a new document or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kháu
    -0.80
    liothèque
    -0.52
     kuhusu
    -0.47
    DrawerToggle
    -0.46
    InsertCommand
    -0.46
    bnf
    -0.46
     horaire
    -0.44
    quelize
    -0.44
     iprot
    -0.44
    тельстве
    -0.43
    POSITIVE LOGITS
    Hochspringen
    1.67
     مشين
    1.66
    tvguidetime
    1.66
    مصادر
    1.64
    Lähteet
    1.63
     références
    1.60
     שוליים
    1.59
    expandindo
    1.54
    Bronnen
    1.53
     autorytatywna
    1.52
    Activations Density 0.029%

    No Known Activations