© 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. 38-GEMMASCOPE-RES-16K
    11. 14051
    Prev
    Next
    INDEX
    Explanations

    references to family gatherings and communal dining experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UserScript
    -0.66
     Drinks
    -0.62
     propOrder
    -0.60
    rungsseite
    -0.60
    <unused14>
    -0.59
    [@BOS@]
    -0.59
    <unused52>
    -0.59
    <unused79>
    -0.59
    <unused23>
    -0.59
    <unused28>
    -0.59
    POSITIVE LOGITS
     slur
    0.65
     wolf
    0.61
     finishing
    0.60
     nos
    0.57
     indulging
    0.56
     gu
    0.55
     finish
    0.54
     sampling
    0.54
     downed
    0.54
     indulge
    0.54
    Activations Density 0.260%

    No Known Activations