© 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. 2125
    Prev
    Next
    INDEX
    Explanations

    references to officials or representatives in governmental contexts

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

    Jordan or capillaries

    np_acts-logits-general · gemini-2.0-flash

    Jordanian embassy spokesman

    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
     Eul
    -0.64
    SurfaceView
    -0.55
    SupportActionBar
    -0.50
     NSCoder
    -0.50
     Melville
    -0.47
     Southampton
    -0.47
     Chow
    -0.47
    atitis
    -0.46
     Nao
    -0.46
     Nami
    -0.45
    POSITIVE LOGITS
     Jordanian
    0.76
     transfieras
    0.72
     Jordan
    0.70
     Amman
    0.68
     dAtA
    0.67
     filtration
    0.65
    Jordan
    0.64
     capillaries
    0.62
    Personendaten
    0.61
     Aq
    0.61
    Activations Density 0.538%

    No Known Activations