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. 4-GEMMASCOPE-RES-16K
    6. 3467
    Prev
    Next
    INDEX
    Explanations

    specific numerical values and parentheses in legal or formal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    @
    -0.48
     samfun
    -0.48
     resistenza
    -0.48
    ساء
    -0.48
     noires
    -0.47
     contenus
    -0.45
     sabbia
    -0.45
     gruppe
    -0.45
     états
    -0.44
     faciles
    -0.44
    POSITIVE LOGITS
     Савезне
    1.09
     Paglinawan
    0.93
    первых
    0.87
     cherchés
    0.86
    webElementXpaths
    0.80
    NUMX
    0.80
    tagHelperRunner
    0.79
    الإنجليزية
    0.79
    IMPORTED
    0.77
     ligiloj
    0.77
    Activations Density 0.689%

    No Known Activations