© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 5769
    Prev
    Next
    INDEX
    Explanations

    emotional expressions related to feelings of shame, pride, and disappointment

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

    Expressing an emotion

    np_acts-logits-general · gemini-2.0-flash

    feelings of pride and disappointment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.81
    divarius
    -0.73
    iddler
    -0.67
    ::__
    -0.64
     parseFrom
    -0.63
    ]='\
    -0.63
    InvalidProtocol
    -0.62
    StoreMessageInfo
    -0.60
    UFACT
    -0.60
    SOUNDBITE
    -0.59
    POSITIVE LOGITS
     surpresa
    0.52
     finding
    0.52
     profundamente
    0.50
     רבה
    0.50
     profondément
    0.49
    不已
    0.47
     crois
    0.46
     how
    0.46
    تیب
    0.45
     beslu
    0.45
    Activations Density 0.156%

    No Known Activations