© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10780
    Prev
    Next
    INDEX
    Explanations

    instances of the word "was" in various contexts

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

    "[Something] was [done/created/written]"

    np_acts-logits-general · gemini-2.0-flash

    was + past participle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.54
    قایناقلار
    -0.50
    NameInMap
    -0.50
     autorytatywna
    -0.45
     nakalista
    -0.43
    matchCondition
    -0.42
    irited
    -0.41
    layoutControl
    -0.41
    ByVersion
    -0.40
     propOrder
    -0.40
    POSITIVE LOGITS
     formerly
    0.68
     recently
    0.62
     früher
    0.59
     previously
    0.58
    recently
    0.58
     vroeger
    0.57
    formerly
    0.57
     recentemente
    0.56
    previously
    0.55
     originally
    0.53
    Activations Density 0.447%

    No Known Activations