© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 12643
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "start" and its variations in the context of programming or initialization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    start actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chieht
    -0.35
     arquitecto
    -0.33
     quien
    -0.32
     jurado
    -0.32
    mauer
    -0.32
    kreises
    -0.31
    versicherung
    -0.30
     Abends
    -0.30
    <bos>
    -0.30
     donors
    -0.30
    POSITIVE LOGITS
     Started
    0.87
     started
    0.86
    Started
    0.82
     Starts
    0.81
     STARTED
    0.78
    started
    0.77
     Begins
    0.77
     Start
    0.77
     starts
    0.76
     start
    0.73
    Activations Density 0.023%

    No Known Activations