© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 3930
    Prev
    Next
    INDEX
    Explanations

    luxury fashion brands and designer items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     feature
    -0.30
     sprend
    -0.28
    FlatAppearance
    -0.28
     Feature
    -0.28
     tikra
    -0.27
     įva
    -0.26
    Feature
    -0.26
     FEATURE
    -0.25
     flecha
    -0.25
    läg
    -0.25
    POSITIVE LOGITS
    enciaga
    0.88
     vuitton
    0.82
    ulemon
    0.79
     EconPapers
    0.79
     ſta
    0.76
    Gucci
    0.75
    ragamo
    0.74
     Vuitton
    0.74
     שוליים
    0.71
    lgari
    0.68
    Activations Density 0.446%

    No Known Activations