Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 2623
    Prev
    Next
    INDEX
    Explanations

    references to musicals and their production elements

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

    musical theatre and performances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.71
     الحره
    -0.61
    exitRule
    -0.55
    ########.
    -0.54
     Wikimedijinoj
    -0.51
    numerusform
    -0.50
    点此举报
    -0.50
     EconPapers
    -0.50
    __((
    -0.50
     kühl
    -0.49
    POSITIVE LOGITS
     musicals
    0.89
    ondheim
    0.67
     Broadway
    0.66
     musical
    0.61
    Broadway
    0.57
     broadway
    0.56
     singing
    0.52
     Musical
    0.52
     Eurovision
    0.50
     choral
    0.47
    Activations Density 0.009%

    No Known Activations