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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7246
    Prev
    Next
    INDEX
    Explanations

    concepts related to ethics and morality in social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.60
     informée
    -0.53
    .)}
    -0.53
     ddelwed
    -0.52
    discovery
    -0.50
    ésultats
    -0.50
     témoig
    -0.50
    StackNavigator
    -0.50
     <<<<<<<<<<<<<<
    -0.49
    kurtka
    -0.49
    POSITIVE LOGITS
     ethical
    0.88
     moral
    0.83
     ethics
    0.81
     Ethical
    0.75
     morality
    0.73
    Ethical
    0.73
     Ethics
    0.70
    moral
    0.70
     ética
    0.70
     ethically
    0.69
    Activations Density 0.468%

    No Known Activations