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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6232
    Prev
    Next
    INDEX
    Explanations

    phrases related to prediction and forecasting

    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
    thansa
    -0.65
    aldehyde
    -0.64
    weile
    -0.63
     pinggang
    -0.61
    üyük
    -0.60
     særlig
    -0.58
    Formazione
    -0.57
    ougou
    -0.56
    liminaries
    -0.56
    grou
    -0.55
    POSITIVE LOGITS
     predict
    2.01
     prediction
    1.97
     predictions
    1.91
     predicts
    1.88
     Predict
    1.85
     Prediction
    1.78
     predicting
    1.77
     Predictions
    1.75
    predict
    1.72
    Predict
    1.71
    Activations Density 0.100%

    No Known Activations