© 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. 13176
    Prev
    Next
    INDEX
    Explanations

    instances of the word "start" or its variations suggesting initiation or beginning

    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
     kasarigan
    -0.59
     Walkover
    -0.58
    fortawesome
    -0.57
     osobow
    -0.52
    tiérrez
    -0.52
     שוליים
    -0.52
     inoxid
    -0.50
    LEncoder
    -0.47
    <unused23>
    -0.47
     パンチラ
    -0.47
    POSITIVE LOGITS
     started
    1.23
    started
    0.99
     Started
    0.90
    Started
    0.85
     STARTED
    0.82
     begun
    0.79
     began
    0.75
     stopped
    0.68
     empezó
    0.68
     starts
    0.65
    Activations Density 0.165%

    No Known Activations