© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 3440
    Prev
    Next
    INDEX
    Explanations

    references to flags, particularly national or symbolic flags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    slidesToShow
    -0.44
    awtextra
    -0.41
     teolog
    -0.38
    rmtree
    -0.37
    Bosch
    -0.35
    FWD
    -0.34
     Réponses
    -0.33
    rehensive
    -0.33
    engertian
    -0.33
     bosch
    -0.33
    POSITIVE LOGITS
     flag
    3.25
     flags
    3.00
     Flag
    2.91
    flag
    2.70
    Flag
    2.64
     Flags
    2.59
     FLAG
    2.50
    flags
    2.36
    Flags
    2.27
     drapeau
    2.22
    Activations Density 0.251%

    No Known Activations