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. 20-GEMMASCOPE-RES-16K
    6. 10041
    Prev
    Next
    INDEX
    Explanations

    instances of adversity and overcoming challenges

    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
     currently
    -0.66
     Currently
    -0.63
    currently
    -0.60
    現在は
    -0.58
    Currently
    -0.57
     bisher
    -0.56
     further
    -0.55
     presently
    -0.53
     현재
    -0.52
     curent
    -0.52
    POSITIVE LOGITS
     бывает
    0.91
     sometimes
    0.86
    Sometimes
    0.82
    sometimes
    0.82
     člověk
    0.80
     člove
    0.77
     solche
    0.76
     Sometimes
    0.76
     člov
    0.74
     آدم
    0.73
    Activations Density 0.521%

    No Known Activations