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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 12943
    Prev
    Next
    INDEX
    Explanations

    conversational expressions indicating personal opinions and experiences

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

    Internet slang and emoticons

    np_acts-logits-general · gemini-2.0-flash

    informal laughter or emoticons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     محفوظة
    -0.70
    ьаж
    -0.68
    ,‎
    -0.66
    InstrumentedTest
    -0.64
    . 
    -0.63
    ".
    
    -0.63
    .•
    -0.63
    \",\"
    -0.63
    SharedDtor
    -0.62
     Мексичка
    -0.62
    POSITIVE LOGITS
     lol
    1.97
     haha
    1.91
     LOL
    1.78
     ;)
    1.76
     hehe
    1.74
     ;-)
    1.73
     :)
    1.70
     Haha
    1.70
     :-)
    1.69
     hahaha
    1.65
    Activations Density 0.550%

    No Known Activations