© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 15361
    Prev
    Next
    INDEX
    Explanations

    references to cybersecurity and quantum computing concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تعدى
    -0.45
    PerformLayout
    -0.43
     jsPsych
    -0.37
    nloa
    -0.37
    Aiheesta
    -0.35
     ब्रेकडाउन
    -0.35
    Discovering
    -0.35
    httphttps
    -0.34
     Wiktionnaire
    -0.34
     newBuilder
    -0.33
    POSITIVE LOGITS
     predictions
    1.35
     prediction
    1.27
     Predictions
    1.20
     predicting
    1.16
     forecasts
    1.13
     predict
    1.13
     forecast
    1.11
    Predictions
    1.11
     predicts
    1.09
     predicted
    1.09
    Activations Density 0.535%

    No Known Activations