© 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. 2-GEMMASCOPE-RES-16K
    11. 1924
    Prev
    Next
    INDEX
    Explanations

    the suffix "ed" in words indicating past tense or completed actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    initializeApp
    -0.75
     CURIAM
    -0.73
     nahilalakip
    -0.71
    RectangleBorder
    -0.69
     Wallflower
    -0.67
     autorytatywna
    -0.67
    pulumi
    -0.61
    urtstag
    -0.61
    tvguidetime
    -0.61
     webdriver
    -0.61
    POSITIVE LOGITS
    ed
    3.43
    ED
    2.27
     ed
    1.65
    eds
    1.53
    Ed
    1.43
    ing
    1.30
     ED
    1.30
    edin
    1.24
     Ed
    1.22
    edc
    1.14
    Activations Density 0.035%

    No Known Activations