© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1237
    Prev
    Next
    INDEX
    Explanations

    entities and references related to social and political controversies surrounding Chick-fil-A and its corporate practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     шо
    -0.25
    \\
    -0.22
     União
    -0.22
    ↵↵
    -0.21
     Unión
    -0.21
     spring
    -0.21
    defined
    -0.21
     sac
    -0.20
     {
    -0.20
     The
    -0.19
    POSITIVE LOGITS
    ImageContext
    0.84
     ujednoznacz
    0.83
     estekak
    0.82
    msgTypes
    0.81
     nonUne
    0.80
    Personendaten
    0.79
    Geplaatst
    0.79
    verwijspagina
    0.78
    httphttps
    0.76
     queſta
    0.76
    Activations Density 0.717%

    No Known Activations