© 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. 38-GEMMASCOPE-RES-16K
    11. 10292
    Prev
    Next
    INDEX
    Explanations

    references to television programs and celebrity-related discussions, particularly in the context of reality TV and the entertainment industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.58
    extAlignment
    -0.51
    AsUp
    -0.50
     مشين
    -0.50
    fjspx
    -0.47
     مواليد
    -0.46
     препратки
    -0.43
    reszcie
    -0.43
     Autorisations
    -0.41
    entance
    -0.41
    POSITIVE LOGITS
     show
    2.47
     shows
    2.19
    show
    1.93
    shows
    1.79
     Shows
    1.71
     Show
    1.67
    Shows
    1.63
     SHOWS
    1.57
     SHOW
    1.57
     шоу
    1.55
    Activations Density 0.444%

    No Known Activations