© 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. 18-GEMMASCOPE-RES-16K
    11. 11124
    Prev
    Next
    INDEX
    Explanations

    terms related to predictive modeling and confidence intervals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    prediction or forecasting

    np_acts-logits-general · gemini-2.0-flash

    prognosis prediction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    بسم
    -0.53
    pha
    -0.45
     keter
    -0.43
    __(/*!
    -0.40
     گوش
    -0.40
    inc
    -0.39
     cher
    -0.38
     tá
    -0.37
     self
    -0.37
    ث
    -0.37
    POSITIVE LOGITS
     prediction
    1.47
     predictions
    1.42
     Prediction
    1.35
     predict
    1.33
     predicting
    1.26
     predicted
    1.25
    Prediction
    1.25
     Predictions
    1.25
     predicts
    1.20
     forecasts
    1.20
    Activations Density 0.170%

    No Known Activations