© 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. 5200
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the importance of specific concepts or qualities, particularly in a formal or structured context

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

    Follows articles "a" or "the"

    np_acts-logits-general · gemini-2.0-flash

    essential concepts

    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
    jíma
    -0.46
     spacy
    -0.46
     novedades
    -0.42
    โปร
    -0.42
    気になった
    -0.42
    想定
    -0.41
    のように
    -0.40
     Retrieved
    -0.39
    気になって
    -0.39
    χρι
    -0.39
    POSITIVE LOGITS
     hallmark
    0.87
     kunci
    0.86
     key
    0.84
     recipe
    0.82
     underrated
    0.81
     keys
    0.81
     superpower
    0.80
     cardinal
    0.77
    🔑
    0.76
    NUMX
    0.76
    Activations Density 0.314%

    No Known Activations