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. 15-GEMMASCOPE-RES-16K
    6. 2286
    Prev
    Next
    INDEX
    Explanations

    verbs and nouns related to attendance or participation in events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    camore
    -0.63
    //
    
    -0.63
    ')))
    -0.63
     negócio
    -0.62
    ("")
    
    -0.61
    مكن
    -0.60
     Luca
    -0.59
     Erm
    -0.59
    ']))
    
    -0.59
    luca
    -0.59
    POSITIVE LOGITS
     attended
    1.36
     attendance
    1.33
     attends
    1.33
     attend
    1.32
     Atten
    1.32
     attending
    1.31
     Attending
    1.27
     Attend
    1.26
    attended
    1.23
    atten
    1.22
    Activations Density 0.192%

    No Known Activations