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. 21-GEMMASCOPE-RES-16K
    6. 6692
    Prev
    Next
    INDEX
    Explanations

    phrases related to reputation and record of success in business contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    AsUp
    -0.60
    ]--;
    -0.58
     <>",
    -0.57
    кульп
    -0.57
    ="#"><
    -0.57
    ViewImports
    -0.56
     <=",
    -0.55
    rzez
    -0.54
    complexContent
    -0.54
    substack
    -0.53
    POSITIVE LOGITS
     record
    2.43
     track
    2.34
    record
    2.04
     Record
    1.94
     RECORD
    1.89
    track
    1.87
    Record
    1.85
     Track
    1.79
    Track
    1.72
     records
    1.68
    Activations Density 0.259%

    No Known Activations