© 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
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 15016
    Prev
    Next
    INDEX
    Explanations

    elements related to fantasy, adventure, and character-driven narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.73
     AssemblyCompany
    -0.67
    そういう
    -0.66
    yntaxException
    -0.63
     nicer
    -0.61
    Хоро
    -0.60
     buenos
    -0.60
    ที่ดี
    -0.60
     좋은
    -0.59
    こういう
    -0.59
    POSITIVE LOGITS
     stunning
    1.13
     captivating
    1.05
     breathtaking
    1.01
     dazzling
    0.94
     spectacular
    0.94
     thrilling
    0.91
     enchanting
    0.89
     sensational
    0.85
     unique
    0.84
     striking
    0.84
    Activations Density 0.395%

    No Known Activations