© 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. 4-GEMMASCOPE-RES-16K
    11. 10344
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to scientific processes and materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.61
    oa̍t
    -0.61
     мәкалә
    -0.59
     OFDb
    -0.57
    Diweddarwch
    -0.57
     bezeichneter
    -0.56
     prawda
    -0.56
    MessageTagHelper
    -0.56
     ويكيپيديا
    -0.55
    Хьажоргаш
    -0.54
    POSITIVE LOGITS
    ceto
    0.61
     nakalista
    0.59
     indig
    0.54
    irah
    0.54
    ImageIO
    0.53
    squareup
    0.52
     Вікі
    0.51
    outon
    0.49
    ocry
    0.49
    CascadeType
    0.49
    Activations Density 0.976%

    No Known Activations