© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 6935
    Prev
    Next
    INDEX
    Explanations

    terms related to predicting outcomes or forecasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    weile
    -0.72
     CommonModule
    -0.70
    openzeppelin
    -0.65
    thansa
    -0.63
    aldehyde
    -0.63
    iParam
    -0.61
     særlig
    -0.61
     trå
    -0.60
     Marlow
    -0.60
    liminaries
    -0.59
    POSITIVE LOGITS
     predict
    2.22
     prediction
    2.18
     predictions
    2.10
     predicts
    2.06
     predicting
    2.02
     Predict
    2.00
     Prediction
    1.98
     Predictions
    1.92
    predict
    1.92
     predicted
    1.89
    Activations Density 0.136%

    No Known Activations