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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 17-GEMMASCOPE-RES-16K
    6. 11030
    Prev
    Next
    INDEX
    Explanations

    HTML comment tags and their associated formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.80
    település
    -0.77
     ffilmiau
    -0.77
    хьтан
    -0.76
    IUrlHelper
    -0.76
    Demografía
    -0.73
     Paglinawan
    -0.73
    IsMutable
    -0.71
    AdapterFactory
    -0.70
    brainly
    -0.70
    POSITIVE LOGITS
    <!--
    1.15
    ><!--
    0.82
     <!--
    0.81
    "><!--
    0.77
     Naga
    0.66
     themſelves
    0.66
    lø
    0.64
     Rä
    0.61
     McIl
    0.60
    icestershire
    0.60
    Activations Density 0.050%

    No Known Activations