© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7118
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "remain" in various tenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     ſche
    -0.65
    courseId
    -0.61
     ſy
    -0.60
     pleaſure
    -0.59
     courseId
    -0.54
    Gauss
    -0.53
    Хьажоргаш
    -0.53
    sci
    -0.53
     ſch
    -0.53
    Candy
    -0.52
    POSITIVE LOGITS
     remain
    0.96
     remains
    0.91
     Remain
    0.90
    Remain
    0.88
    remain
    0.86
     remained
    0.82
     Remains
    0.78
    remains
    0.77
     bleiben
    0.71
     rimane
    0.68
    Activations Density 0.042%

    No Known Activations