© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 12645
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and environmental issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Beres
    -0.93
     Winfrey
    -0.88
     Rha
    -0.87
     tawny
    -0.85
     CreateTagHelper
    -0.84
     CTP
    -0.82
     portuguesa
    -0.80
     Renata
    -0.79
     Duckworth
    -0.79
     Taw
    -0.78
    POSITIVE LOGITS
     kaynağından
    0.80
     Adams
    0.77
     Sasha
    0.74
    WebServlet
    0.73
     Sach
    0.73
    Adams
    0.72
     Trost
    0.70
     dipl
    0.69
     Gerr
    0.69
     Marlins
    0.67
    Activations Density 1.567%

    No Known Activations