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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 4973
    Prev
    Next
    INDEX
    Explanations

    terms 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 @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    twimg
    -0.81
    Jennie
    -0.74
    ochial
    -0.64
    Bum
    -0.64
     aanges
    -0.64
    uckles
    -0.63
     Ebene
    -0.62
     interests
    -0.62
     Dumas
    -0.62
     disampaikan
    -0.61
    POSITIVE LOGITS
     predict
    2.72
     prediction
    2.69
     predictions
    2.47
     predicting
    2.46
     Prediction
    2.40
     predicts
    2.38
     predicted
    2.30
    predict
    2.25
     Predict
    2.21
    prediction
    2.20
    Activations Density 0.081%

    No Known Activations