© 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. 2-GEMMASCOPE-RES-16K
    11. 13072
    Prev
    Next
    INDEX
    Explanations

    the word "ze" and its occurrences in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transférez
    -0.47
    onViewCreated
    -0.45
    帖最后由
    -0.41
     doInBackground
    -0.41
    ChildScrollView
    -0.39
    ????????????????
    -0.38
    zitter
    -0.38
     enro
    -0.38
     decât
    -0.37
    middlewares
    -0.36
    POSITIVE LOGITS
    ze
    0.99
    ZE
    0.69
    ric
    0.64
    Ze
    0.62
     compelling
    0.60
     tragic
    0.60
    MathML
    0.59
    səhifə
    0.58
    rc
    0.57
     Slam
    0.54
    Activations Density 0.704%

    No Known Activations