© 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. 5-GEMMASCOPE-RES-16K
    6. 3702
    Prev
    Next
    INDEX
    Explanations

    instances of the word "conduct" and its variations, indicating a focus on processes or actions related to conducting activities or research

    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
     Clare
    -0.73
    WebVitals
    -0.72
     daisy
    -0.70
     palsy
    -0.70
    ceras
    -0.69
     VES
    -0.68
    KeyListener
    -0.68
     dreamer
    -0.68
     zs
    -0.67
     Arro
    -0.67
    POSITIVE LOGITS
    Conduct
    2.07
     conducted
    2.07
     CONDUCT
    2.05
     Conduct
    2.03
     conduct
    2.01
     conducts
    1.94
    conduct
    1.92
    conducted
    1.82
     conducting
    1.80
     Conducted
    1.73
    Activations Density 0.059%

    No Known Activations