© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 31-GEMMASCOPE-RES-16K
    11. 15094
    Prev
    Next
    INDEX
    Explanations

    references to decorative and themed items for events

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

    decorative tableware and dishware items used in formal dining and tea settings.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.50
    StoryboardSegue
    -0.44
     autorytatywna
    -0.43
    invokeLater
    -0.42
     contextLoads
    -0.42
    phosa
    -0.42
    蒻
    -0.41
     neceſſ
    -0.41
     oczy
    -0.40
    ニーカー
    -0.40
    POSITIVE LOGITS
     tableware
    1.23
     dishes
    1.19
     dish
    1.19
     plates
    1.14
     plate
    1.12
     glassware
    1.10
     cutlery
    1.10
     silverware
    1.07
     Plates
    1.05
     vaisselle
    1.05
    Activations Density 0.164%

    No Known Activations