© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 106686
    Prev
    Next
    INDEX
    Explanations

    references to individuals involved in performance or entertainment

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

    performers and entertainers

    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
    isDebug
    -0.54
     mistake
    -0.47
     diagnoses
    -0.47
     automation
    -0.46
     diagnosis
    -0.46
     diagnosing
    -0.45
    缺
    -0.45
     plan
    -0.45
    ("//
    -0.45
     new
    -0.45
    POSITIVE LOGITS
     performer
    1.85
     performers
    1.72
     Performer
    1.62
     entertainer
    1.05
     entertainers
    0.94
     Perform
    0.85
     PERFORM
    0.78
     intérprete
    0.77
    performing
    0.75
    Perform
    0.74
    Activations Density 0.002%

    No Known Activations