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. 0-GEMMASCOPE-RES-16K
    6. 6797
    Prev
    Next
    INDEX
    Explanations

    instances of the word "drop" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     odkazy
    -0.65
    expandindo
    -0.61
    Portály
    -0.59
    foss
    -0.55
     Uint
    -0.54
     lccn
    -0.54
     tramonto
    -0.54
     lettore
    -0.54
     âme
    -0.54
    esModule
    -0.54
    POSITIVE LOGITS
     drop
    1.19
     Drop
    1.12
    Drop
    1.12
     dropped
    1.06
     drops
    1.05
     dropping
    1.02
    dropping
    0.99
    drop
    0.94
     Drops
    0.91
     DROP
    0.91
    Activations Density 0.102%

    No Known Activations