© 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. 34-GEMMASCOPE-RES-16K
    11. 11884
    Prev
    Next
    INDEX
    Explanations

    references to Christmas decorations and design elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.82
    rungsseite
    -0.72
    writeFieldEnd
    -0.62
    matchCondition
    -0.62
    Personensuche
    -0.60
    ########.
    -0.59
     المعيارى
    -0.57
    awtextra
    -0.57
     autorytatywna
    -0.57
     estekak
    -0.57
    POSITIVE LOGITS
     decoration
    2.53
     decorations
    2.38
     decorate
    2.22
     decorating
    2.22
     decor
    2.16
    Decor
    2.06
     Decoration
    2.06
     Decor
    2.06
     decorated
    2.05
     décor
    2.03
    Activations Density 0.203%

    No Known Activations