© 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. 19-GEMMASCOPE-RES-16K
    11. 8406
    Prev
    Next
    INDEX
    Explanations

    academic references and citations in mathematical literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NoSuchAlgorithm
    -0.47
     pâtes
    -0.47
     secco
    -0.43
     Hypothe
    -0.41
     canst
    -0.40
    greif
    -0.39
    Marshaller
    -0.38
    抱
    -0.38
    ᐅ
    -0.38
     Comparative
    -0.37
    POSITIVE LOGITS
     تضيفلها
    0.84
     يتيمه
    0.83
     betweenstory
    0.83
     المعيارى
    0.77
    {§
    0.76
     kasarigan
    0.75
    abestanden
    0.75
    
    0.74
    homonymie
    0.73
     utafitiHapana
    0.73
    Activations Density 1.080%

    No Known Activations