© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6698
    Prev
    Next
    INDEX
    Explanations

    elements related to film production and scriptwriting

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

    credits and creative roles in the entertainment industry, like writers, authors, composers, and arrangers.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     '{@
    -0.52
    featureID
    -0.51
    ercito
    -0.48
     विश्वसनीयता
    -0.47
    Ladd
    -0.46
    EndContext
    -0.46
    parsedMessage
    -0.45
     fevere
    -0.45
    ="@+
    -0.44
     groet
    -0.44
    POSITIVE LOGITS
     script
    0.59
     screenplay
    0.56
     designing
    0.55
     lyrics
    0.54
     songwriting
    0.54
     penned
    0.53
     written
    0.52
     playwright
    0.52
     design
    0.51
    songwriter
    0.49
    Activations Density 0.081%

    No Known Activations