© 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. 23-GEMMASCOPE-RES-16K
    11. 14872
    Prev
    Next
    INDEX
    Explanations

    comparisons between traditional and modern methods or items

    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
    setVerticalGroup
    -0.70
    brigens
    -0.60
    AntiForgeryToken
    -0.56
    ddots
    -0.55
    setCancelable
    -0.52
     Осо
    -0.51
    MessageTagHelper
    -0.50
    SuppressMessage
    -0.49
     насељу
    -0.49
    nitus
    -0.49
    POSITIVE LOGITS
     traditional
    2.74
     conventional
    2.59
    traditional
    2.43
    Traditional
    2.18
    conventional
    2.14
     Traditional
    2.08
    Conventional
    2.01
     regular
    2.00
     tradicional
    1.98
     Conventional
    1.98
    Activations Density 1.633%

    No Known Activations