© 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. 13-GEMMASCOPE-RES-16K
    11. 8432
    Prev
    Next
    INDEX
    Explanations

    technical details related to stimulation protocols and configurations in experimental settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.53
    
    -0.49
    rolla
    -0.48
    ArrowToggle
    -0.47
    Cyfarwyddwr
    -0.46
    Према
    -0.46
    CRIPTION
    -0.45
    SharedDtor
    -0.43
     nakalista
    -0.42
     ModelRenderer
    -0.42
    POSITIVE LOGITS
     spacing
    0.81
     Spacing
    0.72
     distance
    0.68
     Abstand
    0.68
     spaced
    0.65
    Spacing
    0.65
     Distance
    0.62
     Distances
    0.58
     distancia
    0.58
     jarak
    0.58
    Activations Density 0.911%

    No Known Activations