© 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. 10-GEMMASCOPE-RES-16K
    6. 6359
    Prev
    Next
    INDEX
    Explanations

    structured components in programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "..\..\
    -0.90
     "..\..\..\
    -0.75
    [++
    -0.65
    SharedCtor
    -0.63
    ண்டும்
    -0.62
    พาะ
    -0.62
    hdashline
    -0.57
    hasMoreElements
    -0.56
    AndEndTag
    -0.55
     esportes
    -0.54
    POSITIVE LOGITS
    VersionUID
    0.82
     pyplot
    0.78
    }{*}{}
    0.75
     }</
    0.74
    </caption>
    0.73
    \<^
    0.71
     }}$}
    0.70
    〗
    0.69
    úrese
    0.66
    φάλ
    0.65
    Activations Density 0.070%

    No Known Activations