© 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. 1933
    Prev
    Next
    INDEX
    Explanations

    emotional responses from an audience, particularly during performances or speeches

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

    associated with an audience

    np_acts-logits-general · gemini-2.0-flash

    crowd and audience reactions

    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
     opér
    -0.50
    achten
    -0.46
    rungsseite
    -0.45
    copa
    -0.45
     đôi
    -0.45
     vaga
    -0.44
    setVerticalGroup
    -0.43
    libft
    -0.43
    itakan
    -0.42
     搜索
    -0.42
    POSITIVE LOGITS
     crowd
    1.80
     audience
    1.73
     applause
    1.64
     crowds
    1.63
     Audience
    1.49
    audience
    1.48
    crowd
    1.47
    Audience
    1.43
     audiences
    1.42
     Crowd
    1.41
    Activations Density 0.148%

    No Known Activations