© 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. 20-GEMMASCOPE-RES-16K
    11. 3351
    Prev
    Next
    INDEX
    Explanations

    pronouns and their associated verbs to identify actions and statements about individuals or groups

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

    Following tokens after "Q"

    np_acts-logits-general · gemini-2.0-flash

    Jennings eats

    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
     >=",
    -0.75
     <=",
    -0.75
     فريبيس
    -0.70
    NameInMap
    -0.65
     &___
    -0.60
     Paglinawan
    -0.59
     AllAfrica
    -0.59
    OGND
    -0.57
     Wikidata
    -0.57
     intptr
    -0.55
    POSITIVE LOGITS
     bowiem
    1.17
     totiž
    1.03
     infatti
    1.01
     ведь
    0.96
    だって
    0.87
     einerseits
    0.85
     zwar
    0.82
     certes
    0.80
     misalnya
    0.78
     nemlig
    0.77
    Activations Density 0.494%

    No Known Activations