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. 14377
    Prev
    Next
    INDEX
    Explanations

    phrases related to resilience 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
    出版年
    -0.91
    RuleContext
    -0.72
    OGND
    -0.72
    Tembelea
    -0.67
    IActionResult
    -0.66
     незавершена
    -0.60
    ymce
    -0.55
    }{*}{
    -0.55
    WriteBarrier
    -0.55
    conio
    -0.55
    POSITIVE LOGITS
     courage
    1.60
     brave
    1.51
     courageous
    1.42
     perseverance
    1.40
     resilience
    1.36
     resilient
    1.36
     fortitude
    1.34
     bravery
    1.32
     bravely
    1.30
     persevere
    1.30
    Activations Density 0.321%

    No Known Activations