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. 5480
    Prev
    Next
    INDEX
    Explanations

    structures related to mathematical or logical arrays, especially in the context of linear algebra or matrix representations

    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
    TimeUnit
    -0.58
     Central
    -0.55
    currentThread
    -0.54
    isNameExpr
    -0.52
     DR
    -0.52
    EA
    -0.51
    zigen
    -0.50
     bandes
    -0.50
    mbro
    -0.49
     new
    -0.49
    POSITIVE LOGITS
     дописавши
    1.05
     myſelf
    1.03
     beginnetje
    0.97
    ConstraintMaker
    0.93
     Paglinawan
    0.93
     ivelany
    0.91
    
    0.91
     itſelf
    0.90
    Erreferentziak
    0.90
    verwijspagina
    0.88
    Activations Density 0.019%

    No Known Activations