© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1254
    Prev
    Next
    INDEX
    Explanations

    positive emotions and expressions of happiness

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

    happiness or positive emotions

    np_acts-logits-general · gemini-2.0-flash

    happiness and optimism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     finesse
    -0.45
    ご注意
    -0.39
     save
    -0.39
    importanza
    -0.38
     nonUne
    -0.38
     fascinated
    -0.38
    않
    -0.36
    hilangan
    -0.36
     subtlety
    -0.36
    itoare
    -0.35
    POSITIVE LOGITS
     positivity
    0.80
     upbeat
    0.77
     smile
    0.77
    Smile
    0.77
     cheerful
    0.77
     optimism
    0.76
     Smile
    0.73
    optimis
    0.73
     smiling
    0.72
     smiles
    0.72
    Activations Density 0.362%

    No Known Activations