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

    Neuronpedia

    Jacobian LensNEW
    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. 27-GEMMASCOPE-RES-16K
    11. 8649
    Prev
    Next
    INDEX
    Explanations

    locations and spatial references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     flesta
    -0.34
     illustrationer
    -0.32
     ögon
    -0.30
     enää
    -0.29
     matematika
    -0.29
     soorten
    -0.29
     olyan
    -0.29
     ControllerBase
    -0.29
     everywhere
    -0.28
     anywhere
    -0.28
    POSITIVE LOGITS
    ScopeManager
    0.79
    featureID
    0.75
     تضيفلها
    0.72
     kasarigan
    0.69
     disambiguazione
    0.68
    uxxxx
    0.65
    UnitTesting
    0.65
    хьтан
    0.64
    ViewImports
    0.63
    richTextPanel
    0.63
    Activations Density 0.402%

    No Known Activations