© 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. 21-GEMMASCOPE-RES-16K
    11. 14040
    Prev
    Next
    INDEX
    Explanations

    terms related to operational performance and maintenance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.67
    tanleria
    -0.63
    Geplaatst
    -0.61
    intios
    -0.59
     تضيفلها
    -0.56
    lidays
    -0.55
     CreateTagHelper
    -0.53
    SuspendLayout
    -0.53
    NOPQRST
    -0.52
    mybatisplus
    -0.51
    POSITIVE LOGITS
     operating
    2.16
     functioning
    2.08
     operation
    2.04
     running
    2.00
     operate
    1.93
    operating
    1.83
     operates
    1.82
     operational
    1.77
     operated
    1.75
     Operating
    1.73
    Activations Density 0.594%

    No Known Activations