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. 14402
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Michael" and related identifiers within text

    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
    WebServlet
    -0.70
    ing
    -0.70
     Langer
    -0.69
    исто
    -0.68
     cdti
    -0.67
     Cache
    -0.67
     CONST
    -0.67
    CONST
    -0.66
     touch
    -0.66
     Sext
    -0.66
    POSITIVE LOGITS
     Michael
    1.96
    Michael
    1.78
     MICHAEL
    1.45
    MICHAEL
    1.44
     michael
    1.41
     Michaels
    1.33
    michael
    1.32
    Micha
    1.23
     Mike
    1.14
    micha
    1.06
    Activations Density 0.064%

    No Known Activations