© 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. 6197
    Prev
    Next
    INDEX
    Explanations

    verbs and expressions related to enjoyment or approval

    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
    complex
    -0.44
     dilu
    -0.39
    Ecotoxicity
    -0.39
    body
    -0.38
     Tol
    -0.37
    EndGlobal
    -0.37
     tol
    -0.37
     complex
    -0.37
    igte
    -0.36
     South
    -0.35
    POSITIVE LOGITS
     enjoys
    0.58
     afforded
    0.57
    IsMutable
    0.56
     favoured
    0.52
     enjoyed
    0.52
    受
    0.52
     accorded
    0.50
    受到
    0.50
     được
    0.49
     favored
    0.47
    Activations Density 0.414%

    No Known Activations