© 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. 1-GEMMASCOPE-RES-16K
    11. 2862
    Prev
    Next
    INDEX
    Explanations

    XML or HTML tags and their structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Савезне
    -0.75
     Keuangan
    -0.63
     tästä
    -0.61
     aikaa
    -0.60
     vastaan
    -0.57
    visející
    -0.57
     henkilö
    -0.57
     âmes
    -0.56
     wikipagina
    -0.56
     kautta
    -0.56
    POSITIVE LOGITS
    0.97
    _

    0.69
    -

    0.67
     FA
    0.66
    -
    0.66
    _
    0.66
     Fa
    0.65
     EMP
    0.65
     ICE
    0.65
     OC
    0.64
    Activations Density 0.146%
    No Known Activations