© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 8376
    Prev
    Next
    INDEX
    Explanations

    instances of the word "arrangement" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     actionMode
    -0.47
    hoeddwyd
    -0.45
    Rohy
    -0.44
     Whilst
    -0.42
     cão
    -0.39
     esclavos
    -0.38
     szk
    -0.38
    TextBoxColumn
    -0.38
    Whilst
    -0.37
     whilst
    -0.37
    POSITIVE LOGITS
     arrangement
    0.68
     heels
    0.62
    arrangement
    0.60
     مرئيه
    0.60
     heel
    0.55
     proposal
    0.54
     ARRANG
    0.53
     invitation
    0.53
     hospitality
    0.52
     Arrangement
    0.51
    Activations Density 0.473%

    No Known Activations