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. 5-GEMMASCOPE-RES-16K
    6. 13269
    Prev
    Next
    INDEX
    Explanations

    references to ceremonies and related attitudes or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.95
     Isola
    -0.77
     dynam
    -0.75
     EconPapers
    -0.74
     neri
    -0.71
    EnableWeb
    -0.70
     Heine
    -0.69
    ctez
    -0.69
     Strickland
    -0.69
     Launch
    -0.69
    POSITIVE LOGITS
     ceremonies
    0.73
     Ceremon
    0.73
    CodedInputStream
    0.72
     ceremony
    0.71
     defaultstate
    0.70
    Attitude
    0.70
    igrette
    0.69
     Attitude
    0.69
    obey
    0.69
    VIAF
    0.69
    Activations Density 0.214%

    No Known Activations