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

    Neuronpedia

    APICircuit 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. 11-GEMMASCOPE-RES-16K
    6. 5754
    Prev
    Next
    INDEX
    Explanations

    references to prediction and forecasting concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    memberId
    -0.65
     dalamnya
    -0.64
    aldehyde
    -0.62
    astricht
    -0.61
     Maier
    -0.60
    руппа
    -0.60
    üyük
    -0.59
     pinggang
    -0.59
     Jaffe
    -0.58
    ГЛА
    -0.58
    POSITIVE LOGITS
     predict
    1.51
     prediction
    1.46
     predictions
    1.44
     Predict
    1.43
     predicts
    1.42
     Prediction
    1.35
     predicting
    1.33
     Predictions
    1.32
     PRED
    1.31
    predict
    1.28
    Activations Density 0.083%

    No Known Activations