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. 15-GEMMASCOPE-RES-16K
    6. 2447
    Prev
    Next
    INDEX
    Explanations

    themes related to social justice and community service

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.65
    IsMutable
    -0.62
    yntaxException
    -0.61
     initComponents
    -0.56
    oredCriteria
    -0.53
    <eos>
    -0.53
     Meksiku
    -0.52
     oprot
    -0.50
    LYN
    -0.48
     Fer
    -0.47
    POSITIVE LOGITS
     cérami
    0.76
    出版年
    0.70
     miliardi
    0.66
     préfé
    0.66
     vérit
    0.65
    providedIn
    0.65
     sauvages
    0.64
     ouvriers
    0.63
     tarko
    0.62
     prêtres
    0.61
    Activations Density 0.514%

    No Known Activations