© 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. 37-GEMMASCOPE-RES-16K
    11. 4325
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate restrictions or limitations related to legal or commercial contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     both
    -1.09
    both
    -0.95
     zarówno
    -0.91
     både
    -0.82
     zowel
    -0.82
    BOTH
    -0.81
     sowohl
    -0.81
    Both
    -0.79
     BOTH
    -0.74
     Both
    -0.73
    POSITIVE LOGITS
     selve
    0.80
     själva
    0.72
     estrictamente
    0.71
    immediate
    0.69
     immediate
    0.69
     basics
    0.68
    :✨
    0.65
     strictly
    0.65
    少数
    0.64
     essentials
    0.63
    Activations Density 0.929%

    No Known Activations