© 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. 0-GEMMASCOPE-RES-16K
    11. 2615
    Prev
    Next
    INDEX
    Explanations

    words indicating incompleteness or that something is not wholly addressed or fulfilled

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Económica
    -0.66
     Unterschiede
    -0.62
     Verhandlungen
    -0.61
     econômica
    -0.59
    Conclusión
    -0.59
     Constitucional
    -0.58
     Küste
    -0.57
     Ausbau
    -0.57
     antemano
    -0.57
     conclusiones
    -0.57
    POSITIVE LOGITS
     partial
    1.08
     Partial
    1.07
     partially
    0.97
     Partially
    0.95
    Partial
    0.85
    Parti
    0.84
    parti
    0.84
    partial
    0.78
     sorted
    0.78
     Sorted
    0.78
    Activations Density 0.219%

    No Known Activations