© 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. 3-GEMMASCOPE-RES-16K
    11. 8774
    Prev
    Next
    INDEX
    Explanations

    instances of ridicule and criticism, particularly related to social behaviors or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Chham
    -0.62
    ợp
    -0.59
    GEBURTS
    -0.56
     Escor
    -0.56
     Sequ
    -0.55
    zkiem
    -0.53
    Sequ
    -0.53
    pfung
    -0.53
    коменду
    -0.52
     Ando
    -0.52
    POSITIVE LOGITS
     ridicule
    1.19
     mocking
    1.15
     mocked
    1.09
     mockery
    1.05
     laugh
    1.02
     mocks
    0.96
     ridiculed
    0.96
    laughing
    0.95
     scorn
    0.95
     contempt
    0.95
    Activations Density 0.388%

    No Known Activations