© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 9024
    Prev
    Next
    INDEX
    Explanations

    sections of the document that contain technical or scientific terminology

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

    Prepositions and articles following short tokens

    np_acts-logits-general · gemini-2.0-flash

    Madagascar, Ny, Congo, Rwanda

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alberta
    -0.75
    Alberta
    -0.72
     Vancouver
    -0.61
     Dene
    -0.61
     Calgary
    -0.57
     Banff
    -0.55
     UBC
    -0.54
     Baja
    -0.53
    Punj
    -0.52
     Okan
    -0.52
    POSITIVE LOGITS
     Madagascar
    1.08
    Madagascar
    0.95
    AndEndTag
    0.84
     يتيمه
    0.76
     Ny
    0.73
    Ny
    0.72
     izay
    0.69
     intptr
    0.69
     MonoBehaviour
    0.68
    StoryboardSegue
    0.67
    Activations Density 0.043%

    No Known Activations