© 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. 2-GEMMASCOPE-RES-16K
    6. 5501
    Prev
    Next
    INDEX
    Explanations

    code-related structures and definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ويكيميديا
    -0.66
    onAttach
    -0.63
     BoxFit
    -0.62
     createState
    -0.60
    qrst
    -0.58
     himo
    -0.57
     الفلك
    -0.57
    principalTable
    -0.57
    ArrowToggle
    -0.57
    LLocation
    -0.56
    POSITIVE LOGITS
    awtextra
    0.86
    #
    0.57
    例文帳に追加
    0.55
    LayoutConstraint
    0.52
    rawDesc
    0.52
    )}</
    0.51
    consulté
    0.49
    Искәрмәләр
    0.49
     שוליים
    0.49
    ="//
    0.48
    Activations Density 0.152%

    No Known Activations