© 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. 23-GEMMASCOPE-RES-16K
    6. 9341
    Prev
    Next
    INDEX
    Explanations

    discussions about the importance and experience of sewing and creativity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disposiciones
    -0.49
     FetchType
    -0.46
     contratto
    -0.45
     conformité
    -0.41
     législation
    -0.39
     Wahrnehmung
    -0.38
     ketat
    -0.38
     maintien
    -0.38
     bancaria
    -0.37
     vertrou
    -0.36
    POSITIVE LOGITS
     DIY
    0.88
    DIY
    0.84
     craft
    0.82
     artisan
    0.81
     crafting
    0.79
     crafts
    0.78
     handicrafts
    0.77
     artisans
    0.73
     Crafting
    0.73
     artisanal
    0.72
    Activations Density 0.406%

    No Known Activations