© 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. 37-GEMMASCOPE-RES-16K
    11. 5907
    Prev
    Next
    INDEX
    Explanations

    connections between characters and their emotional development or social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chwiliwch
    -0.50
     resourceCulture
    -0.46
    RegistryLite
    -0.40
    üyada
    -0.40
    addContainerGap
    -0.40
    RenderAtEndOf
    -0.38
    CloseOperation
    -0.35
    endphp
    -0.35
     հղումներ
    -0.35
    SourceChecksum
    -0.35
    POSITIVE LOGITS
     doesn
    2.66
    doesn
    2.27
     didn
    2.19
     don
    2.19
     Doesn
    2.11
    Doesn
    2.03
     isn
    1.75
    didn
    1.74
     doesnt
    1.73
     aren
    1.64
    Activations Density 1.917%

    No Known Activations