© 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. 28-GEMMASCOPE-RES-16K
    11. 4179
    Prev
    Next
    INDEX
    Explanations

    expressions of embarrassment or feelings related to shame

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    feeling embarrassed or ashamed

    np_acts-logits-general · gemini-2.0-flash

    embarrassment and shame

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IBarButtonItem
    -0.39
     Neutral
    -0.37
     prosp
    -0.36
     Kebijakan
    -0.35
     peper
    -0.35
     бла
    -0.35
     jura
    -0.35
    éric
    -0.35
    posit
    -0.34
    setProperty
    -0.34
    POSITIVE LOGITS
     embarrassment
    1.95
     embarrassing
    1.91
     embarrassed
    1.87
     embarrass
    1.75
    Embar
    1.73
     Embar
    1.73
    embar
    1.56
     shame
    1.54
     humiliation
    1.53
     ashamed
    1.51
    Activations Density 0.277%

    No Known Activations