© 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. 1-GEMMASCOPE-RES-16K
    11. 2691
    Prev
    Next
    INDEX
    Explanations

    instances of the word "action" 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 @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.52
     beraber
    -0.39
    MemoryWarning
    -0.39
     fought
    -0.38
     getF
    -0.37
     preocupes
    -0.37
     emailAlready
    -0.35
    épisode
    -0.35
     Zweifel
    -0.34
    見えない
    -0.34
    POSITIVE LOGITS
     action
    3.73
     Action
    3.30
    action
    3.20
    Action
    3.14
     ACTION
    2.95
     acción
    2.73
    ACTION
    2.48
     ação
    2.36
     actions
    2.34
     Actions
    2.34
    Activations Density 0.279%

    No Known Activations