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. 12691
    Prev
    Next
    INDEX
    Explanations

    concepts related to ethics and ethical conduct

    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
     يتيمه
    -0.79
     Audiodateien
    -0.75
    kháu
    -0.74
     chariots
    -0.68
    原始内容存档于
    -0.68
    phylococcus
    -0.66
    addPreferredGap
    -0.65
    IContainer
    -0.65
    FailureListener
    -0.64
     Exacts
    -0.64
    POSITIVE LOGITS
     ethics
    2.21
     ethical
    2.03
    ethics
    1.94
     Ethics
    1.93
    Ethics
    1.84
    ethical
    1.84
     ethically
    1.72
     Ethical
    1.72
    Ethical
    1.60
     ethic
    1.53
    Activations Density 0.173%

    No Known Activations