© 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. 5-GEMMASCOPE-RES-16K
    11. 5105
    Prev
    Next
    INDEX
    Explanations

    relative clauses and phrases that provide additional information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.64
     détail
    -0.61
    Θ
    -0.59
     vägen
    -0.57
     publiek
    -0.57
     muſt
    -0.57
    hyrchwyd
    -0.57
     becauſe
    -0.57
    DoubleQuotes
    -0.57
     dépôt
    -0.56
    POSITIVE LOGITS
     wherein
    0.90
     whereby
    0.87
    wherein
    0.84
     waarbij
    0.83
     where
    0.73
     involving
    0.67
     INVOL
    0.65
     hvor
    0.65
     kdy
    0.65
     जहां
    0.61
    Activations Density 0.356%

    No Known Activations