© 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. 23-GEMMASCOPE-RES-16K
    6. 14242
    Prev
    Next
    INDEX
    Explanations

    technical descriptions of methods or systems that highlight advantages and efficiency

    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
    AndEndTag
    -0.68
     يتيمه
    -0.59
     autorytatywna
    -0.59
    ValueStyle
    -0.58
    ureusement
    -0.56
     connexes
    -0.56
    Дереккөздер
    -0.55
     препратки
    -0.54
    importanza
    -0.54
    IonicModule
    -0.52
    POSITIVE LOGITS
     inexpensive
    1.22
     flexible
    1.22
     cheap
    1.21
     cost
    1.21
     reliable
    1.20
     versatile
    1.14
     economical
    1.11
     efficient
    1.10
     scalable
    1.09
     affordable
    1.06
    Activations Density 0.759%

    No Known Activations