© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 103361
    Prev
    Next
    INDEX
    Explanations

    instances of the word "but" and its contextual variations indicating contrast or exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    windowFixed
    -0.68
    addContainerGap
    -0.61
    ContentLoaded
    -0.60
    fromnode
    -0.60
    BagLayout
    -0.57
    JspWriter
    -0.56
    PreferredItem
    -0.55
    orianCalendar
    -0.54
     Experiment
    -0.53
    sidemargin
    -0.52
    POSITIVE LOGITS
     Viitattu
    0.34
    faßt
    0.32
    心
    0.30
    Nairobi
    0.29
    Madrid
    0.28
    ().
    0.28
    MPL
    0.27
    |()
    0.27
    )))));
    0.27
     пря
    0.26
    Activations Density 0.028%

    No Known Activations