© 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. 3724
    Prev
    Next
    INDEX
    Explanations

    references to political events and changes

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

    Prepositions and the word "the"

    np_acts-logits-general · gemini-2.0-flash

    political and public order issues

    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
     nahilalakip
    -0.71
     Unfortunately
    -0.68
    Unfortunately
    -0.65
    heureusement
    -0.57
    LookAnd
    -0.54
     Honorable
    -0.51
     Fortunately
    -0.50
    Leider
    -0.49
    Honorable
    -0.49
    某
    -0.49
    POSITIVE LOGITS
     defences
    0.83
     ageing
    0.81
     graft
    0.79
     curbs
    0.77
     neighbours
    0.77
     neighbour
    0.75
     AFP
    0.75
     organisers
    0.74
     armour
    0.73
    OGND
    0.73
    Activations Density 0.223%

    No Known Activations