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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 6108
    Prev
    Next
    INDEX
    Explanations

    function and method calls in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     universel
    -0.67
    ุม
    -0.61
    kori
    -0.61
    Strat
    -0.60
    lfloor
    -0.58
    лаш
    -0.58
    avenir
    -0.56
    NameInMap
    -0.55
     universelle
    -0.55
     prevalent
    -0.55
    POSITIVE LOGITS
     ()
    1.45
    (()
    1.29
    ={()
    1.06
     (()
    0.98
     оригіналу
    0.95
     ())
    0.95
    |()
    0.91
     (),
    0.88
     apologise
    0.80
    >)
    0.77
    Activations Density 0.032%

    No Known Activations