© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15287
    Prev
    Next
    INDEX
    Explanations

    references to scientific studies and data points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     ainfi
    -0.66
     négo
    -0.66
     heureuse
    -0.65
     plufieurs
    -0.65
     puissante
    -0.64
     miniaturka
    -0.63
     sprawy
    -0.60
     wytrzyma
    -0.60
     faſt
    -0.60
     anún
    -0.59
    POSITIVE LOGITS
     Dons
    0.57
    IOD
    0.57
     ODS
    0.55
    Ode
    0.54
    ocs
    0.54
    poch
    0.54
    poc
    0.54
    OCT
    0.54
     })}
    0.52
    ')"
    0.52
    Activations Density 0.669%

    No Known Activations