© 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. 36-GEMMASCOPE-RES-16K
    11. 8243
    Prev
    Next
    INDEX
    Explanations

    important events or announcements related to business or organizational changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tembelea
    -0.60
     useAppContext
    -0.54
     Савезне
    -0.54
    Enllaces
    -0.47
     BorderSide
    -0.46
    Referencies
    -0.45
    AnchorStyles
    -0.44
    MLLoader
    -0.44
    ſelf
    -0.44
     vedno
    -0.44
    POSITIVE LOGITS
     marks
    1.21
     follows
    1.08
     coincides
    1.02
     coincided
    0.94
    marks
    0.87
     comes
    0.85
    follows
    0.85
     represents
    0.77
     builds
    0.77
     Follows
    0.76
    Activations Density 0.562%

    No Known Activations