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. 4515
    Prev
    Next
    INDEX
    Explanations

    discussions of legal duties and responsibilities

    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
    -1.02
    parsedMessage
    -0.79
     Exacts
    -0.75
     Arian
    -0.74
     pymongo
    -0.73
     élector
    -0.73
     phoenix
    -0.72
     Maia
    -0.72
     solstice
    -0.72
     useStyles
    -0.71
    POSITIVE LOGITS
     duty
    2.24
     Duty
    1.91
     duties
    1.89
    duty
    1.87
     DUTY
    1.77
    Duty
    1.76
     obligation
    1.75
     Duties
    1.68
     obligations
    1.60
    Duties
    1.54
    Activations Density 0.138%

    No Known Activations