© 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. 4-GEMMASCOPE-RES-16K
    6. 2631
    Prev
    Next
    INDEX
    Explanations

    numbers and numerical values, often in a scientific or legal context

    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
    tagHelper
    -0.68
    IBILITIES
    -0.65
    httphttps
    -0.64
    OTHY
    -0.62
     poto
    -0.61
     prostu
    -0.61
    tvguidetime
    -0.60
     ویکی‌پدیای
    -0.60
    춘
    -0.60
    msgTypes
    -0.60
    POSITIVE LOGITS
    iotensin
    0.66
    ણી
    0.64
     asl
    0.61
    pidou
    0.60
    DataAnnotations
    0.60
    crom
    0.59
     Egger
    0.59
     Ome
    0.59
     xlink
    0.58
    arange
    0.57
    Activations Density 0.387%

    No Known Activations