Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 8049
    Prev
    Next
    INDEX
    Explanations

    elements related to community infrastructure and governance

    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
     Kriege
    -0.28
     Mensch
    -0.28
    ViewData
    -0.27
     geslacht
    -0.27
     Meldung
    -0.27
     Arbeiten
    -0.27
     Gewalt
    -0.27
     politika
    -0.26
     Anmeldung
    -0.26
     Nederlandse
    -0.26
    POSITIVE LOGITS
     gymnasium
    1.43
     hotel
    1.41
     hospital
    1.40
     museum
    1.39
     mosque
    1.36
     monastery
    1.36
     synagogue
    1.36
     motel
    1.33
     orphanage
    1.32
     hostel
    1.31
    Activations Density 0.927%

    No Known Activations