© 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. 3-GEMMASCOPE-RES-16K
    11. 11433
    Prev
    Next
    INDEX
    Explanations

    terms associated with motherhood and family-related celebrations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     such
    -0.40
     kil
    -0.36
    ↵↵
    -0.35
    Transport
    -0.35
     given
    -0.35
     Neub
    -0.35
     Reif
    -0.34
     Urban
    -0.34
     put
    -0.34
    training
    -0.33
    POSITIVE LOGITS
    RenderAtEndOf
    0.65
     MainAxisSize
    0.65
    fillType
    0.63
    الحياه
    0.63
    Chham
    0.61
    AndroidJUnit
    0.59
     AssemblyCompany
    0.56
    rbrakk
    0.54
     increí
    0.54
    Personensuche
    0.54
    Activations Density 2.272%

    No Known Activations