© 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. 90970
    Prev
    Next
    INDEX
    Explanations

    programming constructs and functions in code

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

    this

    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
    AddTagHelper
    -1.01
    awtextra
    -0.90
    новниш
    -0.80
     EconPapers
    -0.79
    expandindo
    -0.79
     kasarigan
    -0.78
    ActionCreators
    -0.77
    writeField
    -0.75
     незавершена
    -0.75
     CreateTagHelper
    -0.74
    POSITIVE LOGITS
     adaptar
    0.28
     принять
    0.24
     wear
    0.24
     робити
    0.24
     adecu
    0.24
     henkilö
    0.23
     interpretive
    0.23
     добраться
    0.22
     Wirken
    0.22
     Annahme
    0.22
    Activations Density 0.006%

    No Known Activations