© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15055
    Prev
    Next
    INDEX
    Explanations

    positive adjectives describing quality or excellence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     remit
    -0.37
     lawsuits
    -0.35
     nawr
    -0.35
     lawsuit
    -0.35
    Filmo
    -0.34
     Sheehan
    -0.33
     tri
    -0.33
    Bagi
    -0.33
     backlash
    -0.32
    Dabei
    -0.32
    POSITIVE LOGITS
     good
    1.13
    excellent
    1.08
    good
    1.08
     excellent
    1.02
    Good
    1.01
    Excellent
    0.98
     excelente
    0.95
     Good
    0.95
     Excellent
    0.95
     Хоро
    0.94
    Activations Density 0.310%

    No Known Activations