© 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. 9-GEMMASCOPE-RES-16K
    11. 14490
    Prev
    Next
    INDEX
    Explanations

    references to online accessibility or content

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     shall
    -0.44
     Capacidad
    -0.43
     Estructura
    -0.41
     polecam
    -0.41
     możliwość
    -0.41
    Lieferumfang
    -0.40
    Exemples
    -0.40
     bapak
    -0.40
     recomenda
    -0.40
     pomysł
    -0.39
    POSITIVE LOGITS
     online
    2.20
     Online
    2.00
    online
    1.98
    Online
    1.97
     ONLINE
    1.91
    ONLINE
    1.78
     онлайн
    1.51
     offline
    1.40
    在线
    1.35
     Offline
    1.34
    Activations Density 0.062%

    No Known Activations