© 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. 7315
    Prev
    Next
    INDEX
    Explanations

    verbal constructions indicating possession or existence

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

    Follows "has" or "have" and a past participle

    np_acts-logits-general · gemini-2.0-flash

    has/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
     Jefus
    -0.73
     ChromeDriver
    -0.73
     Chriftian
    -0.72
     Chrift
    -0.68
     neceffary
    -0.68
     circumcision
    -0.67
     againſt
    -0.66
     themſelves
    -0.65
     forze
    -0.65
     MNRAS
    -0.64
    POSITIVE LOGITS
     been
    1.76
     had
    1.25
     got
    1.13
    been
    1.03
     gotten
    1.02
     become
    1.01
     never
    0.93
     already
    0.91
     gone
    0.91
     come
    0.87
    Activations Density 0.485%

    No Known Activations