© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5666
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly geographical names and locations

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

    Following a capitalized word

    np_acts-logits-general · gemini-2.0-flash

    place names and geographical features

    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
     
    -0.81
     the
    -0.68
     once
    -0.66
     online
    -0.65
     "
    -0.65
     one
    -0.63
     a
    -0.62
     only
    -0.60
     final
    -0.59
     over
    -0.59
    POSITIVE LOGITS
     Meksiku
    0.89
     Савезне
    0.88
    OGND
    0.86
     StatelessWidget
    0.85
     Мексичка
    0.79
     IBOutlet
    0.78
    expandindo
    0.78
     photolibrary
    0.77
     AllAfrica
    0.74
     surla
    0.74
    Activations Density 0.288%

    No Known Activations