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. 4747
    Prev
    Next
    INDEX
    Explanations

    phrases related to social commentary and activism

    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
    Искәрмәләр
    -0.62
    endphp
    -0.60
    arynx
    -0.60
    Географиясе
    -0.57
    談社
    -0.56
    reportWebVitals
    -0.56
     solitario
    -0.55
    ParallelGroup
    -0.55
    melons
    -0.55
    πουργ
    -0.55
    POSITIVE LOGITS
     themselves
    1.02
     their
    0.85
    themselves
    0.74
    their
    0.68
    Their
    0.66
     Their
    0.66
     THEIR
    0.64
     kteří
    0.59
     yourselves
    0.59
     theirs
    0.52
    Activations Density 1.067%

    No Known Activations