© 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. 11-GEMMASCOPE-RES-16K
    6. 2531
    Prev
    Next
    INDEX
    Explanations

    sporting events and their outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    営
    -0.54
     Aline
    -0.51
     avanti
    -0.49
    нін
    -0.46
     sprá
    -0.45
    ${
    -0.44
    Gecko
    -0.44
    atrième
    -0.44
    💲
    -0.44
    󠁢
    -0.43
    POSITIVE LOGITS
    complexContent
    0.99
     ivelany
    0.89
    MigrationBuilder
    0.83
     opponents
    0.80
    TintMode
    0.79
     esternos
    0.78
    ArrowToggle
    0.77
    انجليز
    0.72
    HasColumnType
    0.72
    cshtml
    0.71
    Activations Density 0.165%

    No Known Activations