© 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. 11-GEMMASCOPE-RES-16K
    11. 14294
    Prev
    Next
    INDEX
    Explanations

    conditional statements in code that involve logical comparisons and calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Waray
    -0.77
     مشين
    -0.67
    parsedMessage
    -0.67
     Numerade
    -0.63
    تفصیلات
    -0.63
    Identyfik
    -0.62
    RetentionPolicy
    -0.60
    CppMethod
    -0.59
    UpInside
    -0.59
     GAT
    -0.59
    POSITIVE LOGITS
     still
    0.53
    ActivityCompat
    0.51
    солю
    0.51
     AssemblyProduct
    0.48
    ゞ
    0.45
    hock
    0.45
    Према
    0.45
    料
    0.44
    hoven
    0.44
    oral
    0.42
    Activations Density 0.105%

    No Known Activations