© 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. 10-GEMMASCOPE-RES-16K
    11. 11847
    Prev
    Next
    INDEX
    Explanations

    structured references or citations within the text

    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
     للمعارف
    -0.36
     EXT
    -0.36
     generate
    -0.35
     generational
    -0.34
     functional
    -0.33
    HAEL
    -0.32
     eccentric
    -0.32
     PERSONAL
    -0.32
     générer
    -0.31
     ejecutivo
    -0.30
    POSITIVE LOGITS
    BufferException
    0.63
    RUnlock
    0.59
    تقاوى
    0.57
     OGSÅ
    0.56
    úgó
    0.56
    principalColumn
    0.52
     StatelessWidget
    0.50
    outState
    0.49
     createSlice
    0.49
    Datuak
    0.49
    Activations Density 2.672%

    No Known Activations