© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-GEMMASCOPE-RES-16K
    11. 12131
    Prev
    Next
    INDEX
    Explanations

    expressions and terms related to feelings of embarrassment and shame

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.50
    rsiniz
    -0.46
     Direktur
    -0.44
     mandatario
    -0.41
    PreferredItem
    -0.40
     complaint
    -0.36
    riffe
    -0.36
     Administração
    -0.35
     contract
    -0.35
    emoc
    -0.35
    POSITIVE LOGITS
     embarrassment
    1.31
     embarrassing
    1.23
     embarrassed
    1.21
     shame
    1.21
     embarrass
    1.20
     Embar
    1.20
    Embar
    1.20
    shame
    1.10
    embar
    1.09
     Shame
    1.09
    Activations Density 0.214%

    No Known Activations