© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 407
    Prev
    Next
    INDEX
    Explanations

    Java import statements, especially those related to collections such as ArrayList and HashMap

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    المناصب
    -0.71
     Myron
    -0.62
    verwijspagina
    -0.56
     समीक्षाओं
    -0.56
    mphony
    -0.54
    richTextPanel
    -0.53
     Италијани
    -0.52
     Meksiku
    -0.52
    Mex
    -0.51
    hoeddwyd
    -0.51
    POSITIVE LOGITS
     الحره
    0.68
    KommentareTeilen
    0.68
    ElementException
    0.63
    OrNil
    0.62
    printStackTrace
    0.58
    ChildScrollView
    0.55
    inatal
    0.55
     AssemblyCulture
    0.54
     Pingback
    0.54
     ارش
    0.53
    Activations Density 0.008%

    No Known Activations