© 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. 4895
    Prev
    Next
    INDEX
    Explanations

    references to community identity and citizenship issues

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

    Word ending in "s" or possessive "s"

    np_acts-logits-general · gemini-2.0-flash

    possessives followed by descriptions

    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
     pulumi
    -0.68
     Zimbabwe
    -0.59
     Nepal
    -0.58
    GOTREF
    -0.58
     Kenya
    -0.57
     Malaysia
    -0.56
     Florida
    -0.54
     Bangladesh
    -0.54
     Minnesota
    -0.54
     Uganda
    -0.53
    POSITIVE LOGITS
     largest
    0.85
     population
    0.83
     coastline
    0.81
     größ
    0.76
     richest
    0.75
     economy
    0.75
     beaches
    0.74
     finest
    0.72
     Largest
    0.70
     Finest
    0.70
    Activations Density 0.215%

    No Known Activations