© 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. 24-GEMMASCOPE-RES-16K
    6. 12153
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "had" in different contexts

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

    "Had" followed by a past participle

    np_acts-logits-general · gemini-2.0-flash

    past intentions and experiences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Had
    -0.77
     Had
    -0.73
    Искәрмәләр
    -0.65
    had
    -0.61
     actualidad
    -0.55
    ChildScrollView
    -0.54
     имеют
    -0.54
    ValueStyle
    -0.52
    現在は
    -0.52
     had
    -0.50
    POSITIVE LOGITS
     hoped
    1.40
     originally
    1.27
     previously
    1.11
     earlier
    1.09
     initially
    1.05
     intended
    1.02
     ursprünglich
    1.00
     planned
    0.98
    originally
    0.95
    previously
    0.91
    Activations Density 0.146%

    No Known Activations