© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 114199
    Prev
    Next
    INDEX
    Explanations

    words indicating movement or spatial positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    away, up, fire, ground, working, invented

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.66
    
    -0.64
    Atsauces
    -0.60
     kasarigan
    -0.59
     typelib
    -0.58
     voran
    -0.58
    něž
    -0.57
    RTEX
    -0.57
     burgeoning
    -0.56
    modelBuilder
    -0.56
    POSITIVE LOGITS
     airplanes
    0.45
    FUCK
    0.45
     everybody
    0.44
     Anſ
    0.43
     stuff
    0.43
     airplane
    0.42
     spion
    0.41
     Inſ
    0.41
     STUFF
    0.40
    Everybody
    0.40
    Activations Density 0.067%

    No Known Activations