© 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. 3670
    Prev
    Next
    INDEX
    Explanations

    phrases related to error handling in programming

    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
     ());
    -0.60
     eventdata
    -0.56
     فريبيس
    -0.56
     fieldNum
    -0.53
    --){
    -0.50
    :'#
    -0.48
    oples
    -0.48
     ON
    -0.47
    ec
    -0.47
    hasMoreElements
    -0.46
    POSITIVE LOGITS
    throw
    0.96
     démocr
    0.77
    orElseThrow
    0.74
    ResumeLayout
    0.74
    abstractmethod
    0.72
    oforms
    0.71
     télécharge
    0.71
    berdayakan
    0.71
    yakit
    0.71
     mauva
    0.70
    Activations Density 0.013%

    No Known Activations