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. 11-GEMMASCOPE-RES-16K
    6. 5582
    Prev
    Next
    INDEX
    Explanations

    code structures and syntax typical in programming languages, specifically related to control flow and logic statements

    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
    lecte
    -0.49
     hali
    -0.46
    selected
    -0.45
    brano
    -0.45
     crescere
    -0.45
    mą
    -0.45
     gede
    -0.42
     dinyatakan
    -0.42
     seleção
    -0.42
     nacer
    -0.41
    POSITIVE LOGITS
    Билгалдахарш
    1.03
     CreateTagHelper
    0.96
    原始内容存档于
    0.95
    tagHelperRunner
    0.91
    DoubleQuotes
    0.89
     GetEnumerator
    0.88
    ⓧ
    0.86
    queryInterface
    0.83
    Referències
    0.83
     مشين
    0.82
    Activations Density 0.047%

    No Known Activations