© 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. 36-GEMMASCOPE-RES-16K
    11. 8029
    Prev
    Next
    INDEX
    Explanations

    key architectural features and specifications of buildings

    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
    prepareStatement
    -0.58
     Administrativna
    -0.52
    +#+#
    -0.48
    Diweddarwch
    -0.47
    wiada
    -0.47
     propOrder
    -0.46
     CWE
    -0.46
     createSlice
    -0.45
    autique
    -0.45
     dezelve
    -0.44
    POSITIVE LOGITS
     roof
    2.48
     Roof
    2.09
    roof
    2.02
    Roof
    2.00
     roofs
    2.00
     ROOF
    1.93
     roofing
    1.70
     rooftop
    1.65
     rooftops
    1.55
     Rooftop
    1.41
    Activations Density 0.206%

    No Known Activations