© 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. 33-GEMMASCOPE-RES-16K
    11. 3433
    Prev
    Next
    INDEX
    Explanations

    references to the act of writing and literary processes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Comprometido
    -0.49
     habet
    -0.36
     hierro
    -0.36
     aparcamiento
    -0.36
     tatuaje
    -0.36
    IntoConstraints
    -0.36
     Económica
    -0.36
     cuota
    -0.35
     refuerzo
    -0.35
     traslado
    -0.34
    POSITIVE LOGITS
    《
    1.43
     《
    1.16
    『
    1.10
     『
    0.99
    <i>
    0.93
    ：《
    0.91
    <em>
    0.90
    　『
    0.89
     ‘
    0.85
    　　《
    0.82
    Activations Density 1.286%

    No Known Activations