© 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. 8-GEMMASCOPE-RES-16K
    11. 6759
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize opinions or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Parcelize
    -0.34
    s
    -0.34
    sivité
    -0.32
    regelen
    -0.32
     sada
    -0.29
     magnético
    -0.29
    Koordinaten
    -0.28
     た
    -0.28
     ab
    -0.28
    쁜
    -0.27
    POSITIVE LOGITS
    styleType
    0.69
     Paglinawan
    0.68
    Reprodução
    0.59
     AssemblyProduct
    0.58
    BufferException
    0.56
     архивлан
    0.56
     queſta
    0.56
     مشين
    0.55
    principalColumn
    0.55
     ostavi
    0.54
    Activations Density 0.505%

    No Known Activations