© 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. 3665
    Prev
    Next
    INDEX
    Explanations

    specific references to contracts and legal relationships

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

    after capitalized abbreviations

    np_acts-logits-general · gemini-2.0-flash

    specific nouns and their context

    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
     version
    -0.38
     pile
    -0.37
     ber
    -0.36
     screw
    -0.36
     assignment
    -0.35
     unwind
    -0.35
     carrier
    -0.35
     offer
    -0.35
     Ber
    -0.33
     mine
    -0.33
    POSITIVE LOGITS
     nakalista
    0.72
    complexContent
    0.71
     MainAxisSize
    0.70
     препратки
    0.66
     ujednoznacz
    0.63
    ########.
    0.63
    WebElementEntity
    0.62
    makeConstraints
    0.61
    Rptr
    0.61
    ScopeManager
    0.60
    Activations Density 1.231%

    No Known Activations