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. 11-GEMMASCOPE-RES-16K
    6. 6128
    Prev
    Next
    INDEX
    Explanations

    the term "subject" in various contexts related to classification or categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ✨:
    -0.83
     craw
    -0.80
    ForRow
    -0.79
     dandy
    -0.76
    раздо
    -0.76
     Efq
    -0.74
    ="/">
    -0.74
     membuk
    -0.71
     SPS
    -0.71
     flocc
    -0.71
    POSITIVE LOGITS
     subject
    1.93
     Subject
    1.79
    subject
    1.78
     subjects
    1.73
     SUBJECT
    1.70
    Subject
    1.68
    SUBJECT
    1.65
     Subjects
    1.61
    subjects
    1.54
    setSubject
    1.53
    Activations Density 0.062%

    No Known Activations