© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 10689
    Prev
    Next
    INDEX
    Explanations

    the gerund form of verbs, specifically focusing on those ending in 'ging'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.81
     gevolg
    -0.70
    transQ
    -0.57
     propOrder
    -0.56
    帖最后由
    -0.55
     acento
    -0.54
     REA
    -0.53
     Afterward
    -0.52
     Southland
    -0.52
    ieri
    -0.49
    POSITIVE LOGITS
    ging
    3.30
    ged
    2.84
    GING
    2.38
    GED
    1.79
    gings
    1.62
    ges
    1.35
    gingen
    1.31
    Ged
    1.12
    geable
    1.09
     ging
    1.06
    Activations Density 0.073%

    No Known Activations