© 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 EvalsExportsAPI 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. 9563
    Prev
    Next
    INDEX
    Explanations

    special characters and notation commonly used in mathematical expressions or programming syntax

    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
    interopRequire
    -0.40
    Gizmos
    -0.30
     licenci
    -0.30
    bouncycastle
    -0.28
     onely
    -0.26
    madol
    -0.25
     pouss
    -0.24
     Partagez
    -0.24
     gouver
    -0.23
     thither
    -0.23
    POSITIVE LOGITS
     Италијани
    0.81
     ویکی‌پدی
    0.76
    uxxxx
    0.71
     OFDb
    0.71
     betweenstory
    0.70
    Personendaten
    0.70
    rungsseite
    0.68
     autorytatywna
    0.67
     kaarangay
    0.64
     Numerade
    0.63
    Activations Density 1.540%

    No Known Activations