Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 13879
    Prev
    Next
    INDEX
    Explanations

    phrases related to nuclear energy and its development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     everywhere
    -0.64
    brada
    -0.59
     sogget
    -0.59
     للمعارف
    -0.59
     rencontré
    -0.58
    iotensin
    -0.56
    zość
    -0.56
     billions
    -0.55
     loisirs
    -0.55
     apprécié
    -0.54
    POSITIVE LOGITS
     nakalista
    0.76
     apiece
    0.70
    Kaynakça
    0.70
     including
    0.63
    webElementXpaths
    0.63
     continúas
    0.62
    分别是
    0.62
    AnchorStyles
    0.62
    ImageContext
    0.60
     Wikimédia
    0.57
    Activations Density 1.248%

    No Known Activations