© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10107
    Prev
    Next
    INDEX
    Explanations

    documentation and procedural elements in research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulism
    -0.52
     Circ
    -0.50
     spécifique
    -0.49
     résulte
    -0.48
    Shows
    -0.48
     possesso
    -0.47
    dataIndex
    -0.47
     Handwerk
    -0.46
     Defic
    -0.46
     synthèse
    -0.45
    POSITIVE LOGITS
    ItemBackground
    0.70
    RenderAtEndOf
    0.65
    DebuggerNonUser
    0.65
     propOrder
    0.61
     متعلقه
    0.60
     Roskov
    0.58
    !*\
    0.57
     allowed
    0.54
    msgSender
    0.52
    रीदारी
    0.52
    Activations Density 1.204%

    No Known Activations