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. 13-GEMMASCOPE-RES-16K
    6. 6714
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations, particularly in Asia, alongside scientific and technical terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to geographical regions, specifically Asia, and specific scientific concepts or institutions

    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
    </blockquote>
    -0.87
    제
    -0.75
    感
    -0.68
    table
    -0.68
    </em>
    -0.68
     
    -0.67
    ter
    -0.66
     #
    -0.64
     Monter
    -0.62
     the
    -0.61
    POSITIVE LOGITS
     مشين
    1.01
     Torn
    0.97
    peers
    0.90
     Leap
    0.90
    Gaw
    0.90
    picasso
    0.90
     Peers
    0.90
     Gaw
    0.90
    LabelTagHelper
    0.88
     Matka
    0.88
    Activations Density 0.404%

    No Known Activations