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. 21-GEMMASCOPE-RES-16K
    6. 836
    Prev
    Next
    INDEX
    Explanations

    references to library resources and services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.80
     виправивши
    -0.77
     насељу
    -0.68
     sold
    -0.67
     sell
    -0.66
    expandindo
    -0.66
    LookAnd
    -0.65
     protoimpl
    -0.64
     Sell
    -0.62
     OMITBAD
    -0.62
    POSITIVE LOGITS
     library
    1.89
     librarians
    1.73
     Library
    1.65
     librarian
    1.64
     libraries
    1.60
    Library
    1.53
     Libraries
    1.50
     Librarian
    1.49
    library
    1.49
     Librarians
    1.46
    Activations Density 0.119%

    No Known Activations