© 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. 17-GEMMASCOPE-RES-16K
    11. 11413
    Prev
    Next
    INDEX
    Explanations

    mentions of debugging and debug-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegistryLite
    -0.98
     CreateTagHelper
    -0.80
    enterOuterAlt
    -0.79
    IContainer
    -0.79
     NavController
    -0.74
     للاسماء
    -0.73
    antMatchers
    -0.73
     Yorke
    -0.73
     AppModule
    -0.69
    URLException
    -0.67
    POSITIVE LOGITS
    isDebug
    1.13
     DEBUG
    1.04
     debug
    0.99
     Debug
    0.95
    DEBUG
    0.88
     debu
    0.81
     debugging
    0.81
    debug
    0.80
    Debug
    0.76
     Debugging
    0.75
    Activations Density 0.050%

    No Known Activations