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 - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 43258
    Prev
    Next
    INDEX
    Explanations

    various forms of equipment and apparel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    o
    -0.86
    ot
    -0.86
    an
    -0.77
    l
    -0.76
    m
    -0.75
    del
    -0.73
    k
    -0.72
    en
    -0.68
    1
    -0.68
    est
    -0.68
    POSITIVE LOGITS
    bootstrapcdn
    1.14
     estekak
    1.10
    BibitemShut
    1.09
    bibinfo
    1.08
    )";
    
    1.05
     myſelf
    1.04
     itſelf
    1.03
     footwear
    1.02
     iſt
    0.98
    Lycka
    0.96
    Activations Density 0.024%

    No Known Activations