Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 14-GEMMASCOPE-RES-16K
    6. 10599
    Prev
    Next
    INDEX
    Explanations

    discussions regarding the need for tailored programs for different racial or ethnic groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FormState
    -0.65
    parametrize
    -0.54
    serviceWorker
    -0.48
     autorisation
    -0.46
    ว่าง
    -0.46
    migrations
    -0.46
     Fortune
    -0.45
    ราย
    -0.45
    alay
    -0.45
    setDisplay
    -0.45
    POSITIVE LOGITS
     exclusively
    0.95
     khusus
    0.89
     specifically
    0.89
     specific
    0.88
     specialised
    0.86
     specialized
    0.83
     específica
    0.81
    specific
    0.80
    specialized
    0.78
    specifically
    0.78
    Activations Density 0.545%

    No Known Activations