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. 13-GEMMASCOPE-RES-16K
    6. 9812
    Prev
    Next
    INDEX
    Explanations

    code-related keywords and structures in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    исленность
    -0.72
     réglable
    -0.65
     équilibre
    -0.61
     équilibr
    -0.60
     coloré
    -0.59
     OFDb
    -0.58
     bezeichneter
    -0.57
     riemp
    -0.56
     dicendo
    -0.56
    __(/*!
    -0.56
    POSITIVE LOGITS
    ########.
    0.81
    styleUrls
    0.66
    describe
    0.63
    rxjs
    0.62
    ISTR
    0.61
    aarrggbb
    0.59
    _));
    0.57
     Coh
    0.56
    Coh
    0.55
    SearchView
    0.55
    Activations Density 0.031%

    No Known Activations