© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5482
    Prev
    Next
    INDEX
    Explanations

    modal verbs that express intention or conditionality

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

    "Would" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    would like or would be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tembelea
    -0.65
    يكب
    -0.65
     GeoNames
    -0.60
    TextAppearance
    -0.60
    哋
    -0.58
    Πηγή
    -0.58
     שוליים
    -0.58
     Maguire
    -0.58
    Sonstiges
    -0.56
     Conci
    -0.56
    POSITIVE LOGITS
    Would
    0.97
     WOULD
    0.89
     would
    0.89
     Would
    0.89
    would
    0.86
     likely
    0.86
     normally
    0.82
     rather
    0.79
     ideally
    0.78
    ULD
    0.75
    Activations Density 0.185%

    No Known Activations