© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 12128
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals and educational institutions

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

    Proper nouns followed by institutions or locations

    np_acts-logits-general · gemini-2.0-flash

    names followed by institutions or awards

    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
     aliqu
    -0.56
     Szene
    -0.50
     orgasm
    -0.47
     Amiens
    -0.47
     sects
    -0.47
    ſelf
    -0.46
     bony
    -0.46
     monasteries
    -0.45
     desper
    -0.45
     localities
    -0.45
    POSITIVE LOGITS
     Memorial
    1.13
     Foundation
    1.09
    AddTagHelper
    0.96
     memorial
    0.89
    Memorial
    0.87
     Fund
    0.86
    Foundation
    0.84
     foundation
    0.83
     Award
    0.81
    StructEnd
    0.80
    Activations Density 0.178%

    No Known Activations