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. 1-GEMMASCOPE-RES-16K
    6. 13574
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "try" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RetentionPolicy
    -0.77
     NSCoder
    -0.69
     Audiodateien
    -0.68
     MessageBoxIcon
    -0.63
     voeten
    -0.62
     Bayard
    -0.62
     egens
    -0.62
    sidemargin
    -0.61
    kháu
    -0.60
    istoitu
    -0.60
    POSITIVE LOGITS
     try
    3.69
     Try
    3.49
    Try
    3.42
     tries
    3.38
    try
    3.38
     TRY
    3.12
     tried
    3.06
     trying
    2.90
    TRY
    2.86
     Trying
    2.65
    Activations Density 0.112%

    No Known Activations