© 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. 15-GEMMASCOPE-RES-16K
    11. 5750
    Prev
    Next
    INDEX
    Explanations

    multiple mentions of names or terms with high frequency

    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
     ThemeData
    -0.58
    ensical
    -0.56
    selves
    -0.54
     Sepp
    -0.54
    ankind
    -0.53
     behoort
    -0.53
    elry
    -0.52
    cillor
    -0.52
    UnknownFieldSet
    -0.51
    pholes
    -0.50
    POSITIVE LOGITS
     ویکی‌پدیای
    0.74
    Personensuche
    0.63
    expandindo
    0.60
    ftagPool
    0.58
     vostri
    0.58
    Portale
    0.54
    GraphicsUnit
    0.52
    最快更新
    0.51
    Hentet
    0.50
    RefNanny
    0.50
    Activations Density 0.123%

    No Known Activations