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. 6492
    Prev
    Next
    INDEX
    Explanations

    words related to bridges and transitions

    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
     judiciaire
    -0.61
     poudre
    -0.56
     Svensk
    -0.56
    ]!='
    -0.55
     pitié
    -0.53
    日閲覧
    -0.52
    Matin
    -0.51
    IUrlHelper
    -0.50
     πρω
    -0.49
    terus
    -0.49
    POSITIVE LOGITS
    Bridges
    0.93
     bridges
    0.90
     BRID
    0.86
     Bridges
    0.81
    bridges
    0.80
    Bridget
    0.74
    OGND
    0.70
     桥
    0.70
     Brid
    0.70
     bridge
    0.69
    Activations Density 0.154%

    No Known Activations