© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 7822
    Prev
    Next
    INDEX
    Explanations

    programming syntax related to variable declaration and initialization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    transQ
    -0.67
    InputBorder
    -0.57
    empêcher
    -0.52
    Хьажоргаш
    -0.50
     contextLoads
    -0.50
     Signalez
    -0.49
    BoxShadow
    -0.49
    ThroughAttribute
    -0.48
     autorytatywna
    -0.46
    Selfer
    -0.46
    POSITIVE LOGITS
     y
    1.23
     Y
    0.99
    Y
    0.79
     getY
    0.77
    getY
    0.77
    y
    0.73
    setY
    0.69
    ｙ
    0.65
    clientY
    0.57
     translateY
    0.55
    Activations Density 0.580%

    No Known Activations