© 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. 13-GEMMASCOPE-RES-16K
    11. 763
    Prev
    Next
    INDEX
    Explanations

    Java method definitions and access modifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lenker
    -0.84
    TintMode
    -0.73
    estacks
    -0.71
     cherchés
    -0.70
    IonicModule
    -0.69
    oredCriteria
    -0.67
    Controllo
    -0.64
    GEBURTSDATUM
    -0.64
    KommentareTeilen
    -0.64
    WebServlet
    -0.63
    POSITIVE LOGITS
    LayoutStyle
    0.65
    지를
    0.52
     disparu
    0.51
     Kal
    0.50
    himu
    0.49
    rmtree
    0.48
    ETE
    0.48
     Gew
    0.47
    inema
    0.47
     Eber
    0.47
    Activations Density 0.013%

    No Known Activations