© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 106530
    Prev
    Next
    INDEX
    Explanations

    specific numerical data related to scientific measurements and results

    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
    rosen
    -0.50
     bata
    -0.43
     trig
    -0.43
    Обо
    -0.43
    bats
    -0.42
    bap
    -0.41
     trans
    -0.41
    ցված
    -0.40
     HEX
    -0.40
    AccessorTable
    -0.40
    POSITIVE LOGITS
     demografica
    0.57
     respectivamente
    0.48
    Diweddarwch
    0.45
    WithIdentifier
    0.45
     nakalista
    0.43
    IBOutlet
    0.42
     Geschichts
    0.42
     соответственно
    0.42
     respectively
    0.41
    DispatchToProps
    0.40
    Activations Density 0.071%

    No Known Activations