© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 9688
    Prev
    Next
    INDEX
    Explanations

    references to UNESCO-listed sites and cultural heritage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Historic designations or preservation

    np_acts-logits-general · gemini-2.0-flash

    historic preservation UNESCO

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ListItemIcon
    -0.46
     equip
    -0.42
    pertino
    -0.41
    equip
    -0.41
     Equip
    -0.40
     Equipment
    -0.40
     vort
    -0.40
     Cope
    -0.39
    الدراسه
    -0.37
    Compose
    -0.37
    POSITIVE LOGITS
     UNESCO
    1.07
    UNESCO
    0.94
     Unesco
    0.85
     preservation
    0.65
     heritage
    0.64
     Historic
    0.62
     nomination
    0.60
     Patrimonio
    0.59
    Historic
    0.59
    preservation
    0.57
    Activations Density 0.175%

    No Known Activations