Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 2100
    Prev
    Next
    INDEX
    Explanations

    elements of humor and lightheartedness in content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     оригіналу
    -0.78
    {}{}
    -0.70
    ьаж
    -0.65
     كومونز
    -0.65
     lentement
    -0.60
    httphttps
    -0.59
    (!__
    -0.59
     vuitton
    -0.58
     विश्वसनीयता
    -0.58
     immobilier
    -0.58
    POSITIVE LOGITS
     cheerful
    1.13
     joyful
    0.99
     playful
    0.96
     jovial
    0.94
     joyous
    0.90
     cheery
    0.88
     upbeat
    0.88
     alegre
    0.87
     joy
    0.84
     cheerfully
    0.83
    Activations Density 0.332%

    No Known Activations