Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2028
    Prev
    Next
    INDEX
    Explanations

    instances of waiting and lines in social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bruch
    -0.54
    myra
    -0.53
    
    -0.51
    рад
    -0.46
    OLF
    -0.46
     nido
    -0.44
    kapat
    -0.44
    Revenir
    -0.44
    ftrag
    -0.43
    ύν
    -0.43
    POSITIVE LOGITS
     queue
    1.86
     queuing
    1.71
     queues
    1.69
     waiting
    1.63
     wait
    1.56
     Queue
    1.45
     queued
    1.44
     waits
    1.43
     Waiting
    1.40
    queue
    1.40
    Activations Density 0.091%

    No Known Activations