© 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. 20-GEMMASCOPE-RES-16K
    11. 9455
    Prev
    Next
    INDEX
    Explanations

    terms related to the establishment and creation of organizations or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aspek
    -0.44
     nauki
    -0.40
     homicidio
    -0.39
     demasiado
    -0.38
     sorprender
    -0.38
     conclusão
    -0.37
     posled
    -0.35
     liderança
    -0.35
     sorpresas
    -0.35
     sidste
    -0.35
    POSITIVE LOGITS
     dedicated
    0.76
     virtual
    0.65
    dedicated
    0.62
     channel
    0.56
     register
    0.52
    ggle
    0.52
     mini
    0.51
     platform
    0.51
     cyber
    0.50
     dedicate
    0.50
    Activations Density 0.352%

    No Known Activations