Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 2333
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "try"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    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
    -0.63
     للمعارف
    -0.63
    část
    -0.63
     AppBundle
    -0.61
    bination
    -0.60
    NUMX
    -0.59
     perpétu
    -0.59
     infan
    -0.59
     Dickerson
    -0.59
     hinaus
    -0.59
    POSITIVE LOGITS
    try
    1.84
     Try
    1.28
     try
    1.25
    Try
    1.17
    TRY
    1.13
     TRY
    1.02
     tryp
    0.95
     HasFactory
    0.81
     tries
    0.81
     trypsin
    0.77
    Activations Density 0.026%

    No Known Activations