© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 35-GEMMASCOPE-RES-16K
    11. 6300
    Prev
    Next
    INDEX
    Explanations

    technical terms and code-related elements in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ltä
    -1.31
     brasileño
    -1.26
     Atlántico
    -1.10
     británico
    -1.10
     enemigo
    -1.09
     gobernador
    -1.09
     Ejecutivo
    -1.08
     Gobernador
    -1.06
     comunión
    -1.06
     capitán
    -1.06
    POSITIVE LOGITS
     aper
    0.66
     inse
    0.63
     desc
    0.63
     $_"
    0.62
     unic
    0.62
     sequ
    0.61
     conf
    0.61
     sentin
    0.61
     impre
    0.60
     arre
    0.60
    Activations Density 0.239%

    No Known Activations