© 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. 16-GEMMASCOPE-RES-16K
    11. 5840
    Prev
    Next
    INDEX
    Explanations

    patterns and phrases that indicate focus on particular categories or groups

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

    "Of" followed by a personal pronoun

    np_acts-logits-general · gemini-2.0-flash

    of many types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tebal
    -0.60
     føl
    -0.59
    makeConstraints
    -0.59
     ketat
    -0.58
     betrek
    -0.57
    copg
    -0.56
     læng
    -0.55
    yfik
    -0.54
    toft
    -0.53
    uolo
    -0.53
    POSITIVE LOGITS
    expandindo
    0.83
    नलिखित
    0.77
    ]--;
    0.77
     betweenstory
    0.76
     eventdata
    0.69
    Tikang
    0.69
    ;">
    0.67
    fromnode
    0.67
    útbol
    0.67
     Wikimedijinoj
    0.65
    Activations Density 0.105%

    No Known Activations