© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 14474
    Prev
    Next
    INDEX
    Explanations

    references to movement or transitions

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

    Words/phrases preceding "through"

    np_acts-logits-general · gemini-2.0-flash

    passing through

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الدولى
    -0.58
    ьаж
    -0.56
    setVerticalGroup
    -0.55
    GeneratedValue
    -0.54
    WEBPACK
    -0.53
     zufolge
    -0.53
    AnimationsModule
    -0.53
    AFTER
    -0.52
     Италијани
    -0.51
    
    -0.50
    POSITIVE LOGITS
     through
    2.67
    through
    2.07
     Through
    2.03
    Through
    1.99
     THROUGH
    1.91
    THROUGH
    1.63
     attraverso
    1.59
     thru
    1.58
     través
    1.54
     gjennom
    1.52
    Activations Density 0.468%

    No Known Activations