© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14565
    Prev
    Next
    INDEX
    Explanations

    references to programming libraries and their imports

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

    Starts a turn or ends a turn

    np_acts-logits-general · gemini-2.0-flash

    java imports or programming constructs

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     ſche
    -0.68
    ſelves
    -0.66
    ſelf
    -0.64
    EDEFAULT
    -0.63
     auffi
    -0.63
    Cyfarwyddwr
    -0.63
    exitRule
    -0.62
     Infór
    -0.61
     ſind
    -0.60
     itſelf
    -0.60
    POSITIVE LOGITS
     various
    0.40
     several
    0.38
     viewDidLoad
    0.36
     The
    0.35
     a
    0.34
    Order
    0.34
     multiple
    0.34
     propOrder
    0.34
     Clearance
    0.33
     A
    0.33
    Activations Density 0.041%

    No Known Activations