© 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. 1-GEMMASCOPE-RES-16K
    11. 8501
    Prev
    Next
    INDEX
    Explanations

    words indicating disorder or disruptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inerja
    -0.45
     estrategias
    -0.41
     pédagogique
    -0.40
     Estadual
    -0.40
     ситуацию
    -0.40
     sytu
    -0.40
     suspensão
    -0.40
     movilidad
    -0.39
    Personensuche
    -0.39
    queryInterface
    -0.39
    POSITIVE LOGITS
    bitField
    0.74
     relaxed
    0.57
     Galaxy
    0.57
     relaxes
    0.56
     relax
    0.56
     mess
    0.55
    sizeCache
    0.53
     Wars
    0.53
     Relax
    0.52
    Relax
    0.50
    Activations Density 0.227%

    No Known Activations