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

    Neuronpedia

    Jacobian LensNEW
    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. 9404
    Prev
    Next
    INDEX
    Explanations

    the concept of movement or progress through various states or locations

    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
     fós
    -0.60
     Tatsache
    -0.57
     doméstico
    -0.54
    tableFuture
    -0.54
     refuerzo
    -0.49
     proteína
    -0.48
     âgé
    -0.47
     enfans
    -0.46
     larmes
    -0.45
    zerne
    -0.45
    POSITIVE LOGITS
     through
    1.55
    through
    1.52
     Through
    1.48
    Through
    1.47
     THROUGH
    1.38
    THROUGH
    1.24
    Thru
    1.13
     thru
    1.05
     Thru
    1.05
     durch
    0.99
    Activations Density 0.140%

    No Known Activations