© 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. 2-GEMMASCOPE-RES-16K
    11. 8273
    Prev
    Next
    INDEX
    Explanations

    complex and formal expressions related to legal or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     obses
    -0.66
     myſelf
    -0.63
     roam
    -0.63
     sedu
    -0.60
     carefree
    -0.60
     unselfish
    -0.59
     craz
    -0.58
     outdated
    -0.58
     abus
    -0.57
     secr
    -0.57
    POSITIVE LOGITS
     Notwithstanding
    0.94
     adduced
    0.91
     notwithstanding
    0.89
     forthwith
    0.86
     wherein
    0.84
     occasioned
    0.82
     requisite
    0.82
    withstanding
    0.81
     whereupon
    0.80
     Owing
    0.79
    Activations Density 0.855%

    No Known Activations