© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 79883
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts and properties in code syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    mbggenerated
    -0.50
     Ambiental
    -0.42
    transQ
    -0.40
     Infór
    -0.40
    elemField
    -0.39
    儡
    -0.39
    Assessments
    -0.38
     Deshalb
    -0.38
    GEBURTSDATUM
    -0.38
     addObject
    -0.38
    POSITIVE LOGITS
    RenderAtEndOf
    0.78
     flyknit
    0.60
    ghijklmnop
    0.59
    windowFixed
    0.56
    prech
    0.50
     verwijzen
    0.49
     AppCompat
    0.47
     onBind
    0.45
     pseudo
    0.45
    iterran
    0.44
    Activations Density 0.021%

    No Known Activations