© 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-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 5787
    Prev
    Next
    INDEX
    Explanations

    structural elements in code snippets, such as function and method declarations, as well as control flow statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     isolada
    -0.40
     isolado
    -0.38
    地说道
    -0.37
     μά
    -0.35
     Meksika
    -0.34
     Peralta
    -0.34
     Pusat
    -0.34
     PopupWindow
    -0.34
     bornes
    -0.33
     traseiro
    -0.33
    POSITIVE LOGITS
    featureID
    0.83
    RenderAtEndOf
    0.64
    DockStyle
    0.61
    SPATH
    0.60
    :✨
    0.57
     pinulongan
    0.56
    usercontent
    0.55
    fvar
    0.55
    tagext
    0.54
    ArgsConstructor
    0.53
    Activations Density 0.567%

    No Known Activations