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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 8577
    Prev
    Next
    INDEX
    Explanations

    negations and emphatic assertions in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CUL
    -0.49
     CER
    -0.49
     
    -0.48
      
    -0.48
    PY
    -0.48
     
    -0.47
     BIB
    -0.46
     Gees
    -0.46
     GAM
    -0.46
     PY
    -0.46
    POSITIVE LOGITS
     BOTH
    1.57
     ALWAYS
    1.56
     REALLY
    1.56
     VERY
    1.55
     ANYTHING
    1.52
     ANY
    1.52
     NEVER
    1.51
     MANY
    1.51
     ONLY
    1.50
     EVERY
    1.50
    Activations Density 0.498%

    No Known Activations