© 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. 7070
    Prev
    Next
    INDEX
    Explanations

    numeric values and mathematical expressions

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

    Solving equations, especially with negative signs

    np_acts-logits-general · gemini-2.0-flash

    solve for variables

    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
     propOrder
    -0.70
    存于互联网档案馆
    -0.62
    InjectAttribute
    -0.62
     CreateTagHelper
    -0.61
     surla
    -0.61
    WriteTagHelper
    -0.60
     الحره
    -0.59
    
    -0.59
    хьтан
    -0.57
     صوتيه
    -0.57
    POSITIVE LOGITS
     gunung
    0.39
     dignité
    0.38
    뀜
    0.37
     sanitario
    0.37
     étape
    0.34
     paroisse
    0.34
     flèche
    0.33
    jména
    0.33
     Atlántico
    0.33
    듈
    0.33
    Activations Density 4.346%

    No Known Activations