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. 0-GEMMASCOPE-RES-16K
    6. 6347
    Prev
    Next
    INDEX
    Explanations

    references to specific statistical distributions and concepts in mathematics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,:),
    -0.71
    WebMethod
    -0.62
     Winaray
    -0.62
    Geplaatst
    -0.61
    Hauptartikel
    -0.60
    íma
    -0.57
    PMailer
    -0.56
     pyplot
    -0.56
    &__
    -0.56
     Samb
    -0.55
    POSITIVE LOGITS
     Delta
    1.10
     Gamma
    1.08
     gamma
    1.05
    Delta
    1.04
     omega
    1.03
    gamma
    1.03
    Gamma
    0.99
    delta
    0.95
     delta
    0.95
     Omega
    0.94
    Activations Density 3.623%

    No Known Activations