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 - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 36571
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing respect and courteous behavior within a community context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    flutter
    -0.46
    essa
    -0.43
    ))*
    -0.42
    kani
    -0.41
    icker
    -0.40
     Fuchs
    -0.40
    泉
    -0.38
    után
    -0.38
    ssa
    -0.37
    年代
    -0.37
    POSITIVE LOGITS
    CloseOperation
    1.08
     etiquette
    0.80
    bootstrapcdn
    0.77
    ISupport
    0.76
     manners
    0.75
    MemoryWarning
    0.75
     respectful
    0.71
     behavior
    0.69
    frain
    0.67
     Umgang
    0.66
    Activations Density 0.049%

    No Known Activations