© 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. 10-GEMMASCOPE-RES-16K
    11. 16087
    Prev
    Next
    INDEX
    Explanations

    references to hierarchical or nested structures, particularly related to root elements in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MIDDLEWARE
    -0.86
    httphttps
    -0.81
     influenza
    -0.76
     Chamb
    -0.76
     SDC
    -0.74
     carnival
    -0.73
     وتسجيلات
    -0.73
    verwijspagina
    -0.73
    ukkah
    -0.71
     Lari
    -0.70
    POSITIVE LOGITS
     Root
    1.65
     ROOT
    1.63
     root
    1.58
     Roots
    1.57
     roots
    1.57
    ROOT
    1.49
    Roots
    1.45
    roots
    1.43
    Root
    1.43
    root
    1.43
    Activations Density 0.049%

    No Known Activations