© 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. 20-GEMMASCOPE-RES-16K
    11. 3715
    Prev
    Next
    INDEX
    Explanations

    mentions of "hor" or variations thereof, indicating a focus on specific terms related to the word "horizon."

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

    "Hor" followed by various suffixes

    np_acts-logits-general · gemini-2.0-flash

    horseless, horrible, hordeum, hornet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Allein
    -0.59
    ===
    -0.56
    Revenir
    -0.52
    énario
    -0.51
    weit
    -0.50
    ItemBackground
    -0.49
    ervare
    -0.49
     señ
    -0.49
    oleic
    -0.48
    ==>
    -0.48
    POSITIVE LOGITS
     муніципалі
    0.72
     lenker
    0.71
     '\\;'
    0.68
     Hor
    0.64
     hor
    0.64
    Hor
    0.59
     HOR
    0.59
    tvguidetime
    0.57
    évêque
    0.57
     Wör
    0.56
    Activations Density 0.100%

    No Known Activations