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. 4172
    Prev
    Next
    INDEX
    Explanations

    phrases related to social and environmental conditions impacting individuals, particularly in reference to their integration and adaptation in society

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

    adapting or getting used to something

    np_acts-logits-general · gemini-2.0-flash

    adjustment and adaptation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    -0.61
     ISNI
    -0.57
     acides
    -0.49
     histórica
    -0.49
    /></
    -0.45
    metries
    -0.45
     Soler
    -0.44
     Uribe
    -0.44
    RequestParam
    -0.44
     Lösungs
    -0.44
    POSITIVE LOGITS
     adjustment
    1.65
     adaptation
    1.48
     Adjustment
    1.47
     adjusting
    1.47
     adapting
    1.46
     settling
    1.40
    adjustment
    1.37
     Adjusting
    1.35
    Adjust
    1.34
     adjust
    1.33
    Activations Density 0.358%

    No Known Activations