© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 8349
    Prev
    Next
    INDEX
    Explanations

    instances of try-catch blocks in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ranean
    -0.65
     ää
    -0.62
     kiin
    -0.58
     kaik
    -0.57
    wój
    -0.56
     päät
    -0.55
    část
    -0.54
    grunns
    -0.54
     perpétu
    -0.54
    ExtendWith
    -0.53
    POSITIVE LOGITS
    try
    2.25
     Try
    1.62
     try
    1.59
    Try
    1.48
    TRY
    1.45
     TRY
    1.31
     tryp
    1.06
     tries
    1.02
    TryParse
    0.97
     tried
    0.92
    Activations Density 0.026%

    No Known Activations