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. 6447
    Prev
    Next
    INDEX
    Explanations

    references to academic publications or research studies

    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
    rekli
    -0.51
     ffilmiau
    -0.47
    Engineer
    -0.47
    техни
    -0.46
     ENGINEERING
    -0.46
     Technical
    -0.45
    ngdoc
    -0.45
    Spoljašnje
    -0.45
     teknik
    -0.45
     Engineering
    -0.43
    POSITIVE LOGITS
     scholars
    0.91
     studies
    0.83
     scholarship
    0.80
     JSTOR
    0.80
     scholarly
    0.79
     essays
    0.78
    studies
    0.76
     sociology
    0.75
     comparative
    0.75
     analyzes
    0.74
    Activations Density 0.255%

    No Known Activations