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. 2861
    Prev
    Next
    INDEX
    Explanations

    prepositions and spatial relationships

    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
     các
    -0.82
    both
    -0.80
     समीक्षाओं
    -0.76
    Both
    -0.75
     both
    -0.73
    everything
    -0.72
    anything
    -0.72
     любые
    -0.72
     anything
    -0.71
     lahat
    -0.69
    POSITIVE LOGITS
    GEBURTS
    0.74
     CreateTagHelper
    0.68
     فريبيس
    0.62
    httphttps
    0.62
    BoxShadow
    0.56
    mybatisplus
    0.56
    SuspendLayout
    0.55
     إحدى
    0.54
    __':
    
    0.54
    帖最后由
    0.53
    Activations Density 0.454%

    No Known Activations