© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 15491
    Prev
    Next
    INDEX
    Explanations

    temporal references in narrative contexts

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

    "when" followed by a personal pronoun

    np_acts-logits-general · gemini-2.0-flash

    when subject pronouns

    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
    board
    -0.45
     handle
    -0.40
    peta
    -0.39
     screen
    -0.39
    Zitat
    -0.39
    boards
    -0.38
     use
    -0.37
    seurs
    -0.37
     board
    -0.36
     бор
    -0.36
    POSITIVE LOGITS
    enumi
    0.92
     NSCoder
    0.87
    ########.
    0.85
    ItemBackground
    0.75
    enumii
    0.71
    Portale
    0.71
    
    0.70
    تقاوى
    0.68
    KommentareTeilen
    0.68
     EconPapers
    0.68
    Activations Density 0.181%

    No Known Activations