© 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. 23-GEMMASCOPE-RES-16K
    11. 11420
    Prev
    Next
    INDEX
    Explanations

    academic articles and reviews related to scientific research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    saying
    -0.70
     saying
    -0.67
    UGHS
    -0.66
    astify
    -0.65
     незавершена
    -0.64
     NSCoder
    -0.63
     dicendo
    -0.60
    kuuta
    -0.60
     kidding
    -0.60
    ِّف
    -0.59
    POSITIVE LOGITS
     aim
    0.78
     aims
    0.75
     addresses
    0.68
     seeks
    0.67
     attempts
    0.66
     outlines
    0.65
     summarizes
    0.64
     contains
    0.64
     address
    0.62
     comprise
    0.61
    Activations Density 0.763%

    No Known Activations