© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 10088
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "old" and agents, as well as mentions of carbon-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     StatefulWidget
    -0.89
    ']")
    -0.87
     Wikispecies
    -0.81
    AndEndTag
    -0.78
     Seeder
    -0.75
    脚注の使い方
    -0.74
     ujednoznacz
    -0.73
    MockBean
    -0.73
     LoggerFactory
    -0.72
    ]');
    -0.71
    POSITIVE LOGITS
     plan
    0.88
    plan
    0.79
     agent
    0.69
    old
    0.68
    Agent
    0.67
     Agent
    0.62
     performance
    0.61
     Plan
    0.61
    Plan
    0.57
     Mer
    0.56
    Activations Density 0.122%

    No Known Activations