© 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. 3-GEMMASCOPE-RES-16K
    11. 5925
    Prev
    Next
    INDEX
    Explanations

    terms related to triggering actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PMailer
    -0.46
     Dowling
    -0.46
    ########.
    -0.41
     poved
    -0.41
     currentPage
    -0.40
     paying
    -0.40
     onBackPressed
    -0.40
     onPage
    -0.39
    Paying
    -0.39
    MigrationBuilder
    -0.39
    POSITIVE LOGITS
     trigger
    2.14
     triggering
    2.03
     triggers
    2.00
     Trigger
    1.95
    trigger
    1.92
     triggered
    1.90
     Triggers
    1.81
     provoke
    1.77
    Trigger
    1.76
     stimulate
    1.74
    Activations Density 0.188%

    No Known Activations