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. 1-GEMMASCOPE-RES-16K
    6. 13478
    Prev
    Next
    INDEX
    Explanations

    references to comparisons or distinctions among entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.61
     tuturor
    -0.59
     سكانية
    -0.57
     greu
    -0.57
    dotenv
    -0.53
    kendo
    -0.53
     vechi
    -0.52
    TagHelpers
    -0.52
     viață
    -0.51
     Référence
    -0.50
    POSITIVE LOGITS
    roleum
    0.63
    Portail
    0.62
    就是
    0.60
    DoubleQuotes
    0.60
     Ansprüche
    0.59
    providedIn
    0.58
     else
    0.56
    Longrightarrow
    0.55
    toHave
    0.55
    itism
    0.55
    Activations Density 0.198%

    No Known Activations