© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 1848
    Prev
    Next
    INDEX
    Explanations

    a combination of phrases indicative of official or legal terms

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

    diplomacy or quotations

    np_acts-logits-general · gemini-2.0-flash

    referring to sources

    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
     EconPapers
    -0.78
    MigrationBuilder
    -0.73
    verwijspagina
    -0.72
    AddTagHelper
    -0.68
     насељу
    -0.65
     nahilalakip
    -0.64
     autorytatywna
    -0.60
    +#+
    -0.59
     etc
    -0.57
     وتسجيلات
    -0.55
    POSITIVE LOGITS
     refiri
    0.96
     referring
    0.93
     quoting
    0.83
     commenting
    0.83
     kepada
    0.82
     parlando
    0.77
     referencing
    0.77
     citing
    0.77
     quoted
    0.75
     usai
    0.73
    Activations Density 0.084%

    No Known Activations