© 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 EvalsExportsinterp-engineNEWAPI 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. 8287
    Prev
    Next
    INDEX
    Explanations

    prominent characters and power dynamics in narratives

    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
     autorytatywna
    -1.05
     nakalista
    -1.02
     surla
    -0.98
     otomatig
    -0.92
    
    -0.79
    AsUp
    -0.74
    aarrggbb
    -0.73
    Personendaten
    -0.72
    MessageOf
    -0.72
    FunctionFlags
    -0.71
    POSITIVE LOGITS
     opponent
    0.50
     old
    0.42
     boss
    0.40
     situation
    0.39
     little
    0.38
     previous
    0.36
     two
    0.35
     investis
    0.35
     person
    0.33
     so
    0.33
    Activations Density 0.096%

    No Known Activations