© 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. 2677
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and assertions related to possibilities or hypothetical scenarios

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

    Auxiliary verbs like "have," "would," or "could"

    np_acts-logits-general · gemini-2.0-flash

    would have / could have + past participle

    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
    InstrumentedTest
    -0.82
    :✨
    -0.81
     nakalista
    -0.81
    IntoConstraints
    -0.79
     &___
    -0.78
     Roskov
    -0.76
     GenerationType
    -0.73
    ScopeManager
    -0.73
    AutoresizingMask
    -0.72
    XmlAccessorType
    -0.72
    POSITIVE LOGITS
     have
    0.78
     hubiera
    0.76
     gewesen
    0.74
     hubiese
    0.73
     hubieran
    0.70
     hätte
    0.69
     had
    0.68
     been
    0.67
     has
    0.67
     đã
    0.66
    Activations Density 0.249%

    No Known Activations