© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 7216
    Prev
    Next
    INDEX
    Explanations

    technical and mathematical concepts related to quantum computing or information processing

    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
    feinander
    -0.61
     lò
    -0.58
    devise
    -0.57
    iense
    -0.54
    ftagPool
    -0.53
     geldig
    -0.52
    chtigkeit
    -0.52
    джи
    -0.52
    Personensuche
    -0.51
     hObject
    -0.51
    POSITIVE LOGITS
     autorytatywna
    0.84
     typelib
    0.66
    __*/
    0.66
    ///</
    0.64
     Савезне
    0.63
    зулта
    0.62
    RegistryLite
    0.62
    AndroidJUnit
    0.60
     الدولى
    0.59
    setVerticalGroup
    0.56
    Activations Density 0.544%

    No Known Activations