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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 3392
    Prev
    Next
    INDEX
    Explanations

    expressions of personal resilience and overcoming challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    bravery, resilience, and determination

    np_acts-logits-general · gemini-2.0-flash

    determination and overcoming challenges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tembelea
    -0.68
     ExecuteAsync
    -0.64
    IActionResult
    -0.62
    RuleContext
    -0.54
     informée
    -0.53
     createState
    -0.52
    ContentAsync
    -0.51
    RSpec
    -0.51
    出版年
    -0.49
    weile
    -0.48
    POSITIVE LOGITS
     courage
    1.63
     resilience
    1.48
     perseverance
    1.47
     brave
    1.45
     determination
    1.45
     resilient
    1.43
     courageous
    1.41
     fortitude
    1.41
     bravery
    1.38
     bravely
    1.34
    Activations Density 0.379%

    No Known Activations