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

    Neuronpedia

    APICircuit 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. 16-GEMMASCOPE-RES-16K
    6. 12350
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and stories of personal experiences

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

    Text after periods

    np_acts-logits-general · gemini-2.0-flash

    he or she

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ourselves
    -0.72
    istoitu
    -0.69
    AddHtmlAttribute
    -0.64
    enames
    -0.64
     تضيفلها
    -0.63
    )]{
    -0.63
    ]){
    
    -0.63
    ampang
    -0.62
    )];
    
    -0.61
    Aktualisiert
    -0.60
    POSITIVE LOGITS
     he
    0.80
     she
    0.60
     his
    0.59
     mengaku
    0.57
     He
    0.57
    He
    0.57
    的他
    0.55
     niyang
    0.55
     hän
    0.54
    他不
    0.53
    Activations Density 0.282%

    No Known Activations