© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 8220
    Prev
    Next
    INDEX
    Explanations

    emotional expressions, particularly related to embarrassment and attraction

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

    blushing or embarrassment

    np_acts-logits-general · gemini-2.0-flash

    blushing and embarrassment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.69
    zzleHttp
    -0.64
    aarrggbb
    -0.63
    참고
    -0.58
    </tfoot>
    -0.57
    StoryboardSegue
    -0.57
    GeneratedCode
    -0.56
     '\\;'
    -0.54
    RetentionPolicy
    -0.53
    HomeAsUpEnabled
    -0.53
    POSITIVE LOGITS
     blushing
    1.60
     blush
    1.54
     blushed
    1.53
     embarrassed
    1.32
    blush
    1.19
     embarrassment
    1.15
     Blush
    1.14
     shy
    1.05
     flushed
    0.99
    embar
    0.98
    Activations Density 0.103%

    No Known Activations