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. 16-GEMMASCOPE-RES-16K
    6. 6176
    Prev
    Next
    INDEX
    Explanations

    phrases related to community and social programs that support poverty alleviation through microfinance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessType
    -0.61
     kla
    -0.38
     quen
    -0.38
     QT
    -0.37
    abancı
    -0.37
    مم
    -0.37
     filtra
    -0.37
    gg
    -0.36
    filler
    -0.36
     Cou
    -0.36
    POSITIVE LOGITS
    onViewCreated
    0.92
     livelihood
    0.91
     فريبيس
    0.87
     livelihoods
    0.86
    хьтан
    0.82
     beneficiaries
    0.82
    BASELINE
    0.82
     nahilalakip
    0.81
    principalTable
    0.81
     farmers
    0.80
    Activations Density 0.172%

    No Known Activations