© 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. 22-GEMMASCOPE-RES-16K
    11. 12118
    Prev
    Next
    INDEX
    Explanations

    references to the United Nations and its related activities and resolutions

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

    Follows "UN" and precedes organizations/reports

    np_acts-logits-general · gemini-2.0-flash

    UN followed by related entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onBind
    -0.72
    TagMode
    -0.67
    httphttps
    -0.57
     Tare
    -0.56
     EconPapers
    -0.56
    mtrl
    -0.54
     فريبيس
    -0.53
     indisponible
    -0.53
    StoryboardSegue
    -0.52
     gynhyrchwyd
    -0.52
    POSITIVE LOGITS
    揄
    0.54
    mybatisplus
    0.52
     agencies
    0.49
    glDisable
    0.48
     ReactDOM
    0.48
    utrients
    0.47
     verke
    0.45
    surface
    0.45
     surface
    0.45
     agency
    0.45
    Activations Density 0.153%

    No Known Activations