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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 2187
    Prev
    Next
    INDEX
    Explanations

    instances of embarrassment or implications of humiliation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administração
    -0.35
    "));
    -0.33
     иллю
    -0.30
     ske
    -0.30
     mischief
    -0.29
     élevées
    -0.29
    __':
    -0.29
    bezpiec
    -0.28
     baseline
    -0.28
    ốm
    -0.28
    POSITIVE LOGITS
     embarrassment
    1.14
     embarrassing
    1.13
     embarrassed
    1.09
    Embar
    1.05
     embarrass
    1.02
     Embar
    1.01
     humiliating
    0.94
     humiliation
    0.94
    恥ず
    0.90
     shameful
    0.89
    Activations Density 0.334%

    No Known Activations