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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 3709
    Prev
    Next
    INDEX
    Explanations

    references to Hollywood and associated entertainment awards or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flag
    -0.44
     bath
    -0.41
     Assistant
    -0.41
     bed
    -0.41
     provisions
    -0.39
     work
    -0.39
     ordin
    -0.39
    atst
    -0.39
     Nep
    -0.39
    awtextra
    -0.38
    POSITIVE LOGITS
    Hollywood
    0.93
     Hollywood
    0.93
    LLYWOOD
    0.91
     hollywood
    0.83
    hollywood
    0.81
     FASHION
    0.81
    fashion
    0.74
    FASHION
    0.73
     fashion
    0.73
    Bollywood
    0.71
    Activations Density 0.386%

    No Known Activations