© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9814
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to a web development or coding context

    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
    NOPQRST
    -0.50
    UnusedPrivate
    -0.48
    HideFlags
    -0.47
    yntaxException
    -0.41
     Kearns
    -0.37
    rawDesc
    -0.37
    razos
    -0.36
    tanleria
    -0.36
     koń
    -0.36
    |+\
    -0.35
    POSITIVE LOGITS
     card
    0.93
     cards
    0.81
    Card
    0.81
     Card
    0.80
    card
    0.76
     카드
    0.70
    カード
    0.68
    卡片
    0.68
     CARD
    0.68
     tile
    0.66
    Activations Density 0.289%

    No Known Activations