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. 12-GEMMASCOPE-RES-16K
    6. 4207
    Prev
    Next
    INDEX
    Explanations

    expressions of "coolness" or related positive attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebRequest
    -0.85
    protoimpl
    -0.81
    Personensuche
    -0.81
     HasFactory
    -0.73
    ("")]
    -0.72
     ویکی‌آمباردا
    -0.72
     Sankt
    -0.71
     smtplib
    -0.71
     Morm
    -0.70
     XMLHttpRequest
    -0.69
    POSITIVE LOGITS
     COOL
    1.62
     Cool
    1.61
    Cool
    1.50
    cool
    1.50
    COOL
    1.47
     cool
    1.41
     cools
    1.37
     cooler
    1.16
     coolest
    1.16
     coolness
    1.15
    Activations Density 0.074%

    No Known Activations