© 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. 9-GEMMASCOPE-RES-16K
    11. 8140
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the quality or condition of an object or concept

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sándor
    -0.57
     dét
    -0.53
    はず
    -0.52
    ỉ
    -0.49
    说什么
    -0.49
     erfüllt
    -0.49
    toEqual
    -0.49
    する
    -0.48
     ער
    -0.47
    phoric
    -0.47
    POSITIVE LOGITS
    AsUp
    0.95
     فريبيس
    0.85
     autorytatywna
    0.83
    ">//
    0.79
     insuffisamment
    0.77
    fromnode
    0.77
     betweenstory
    0.76
     kasarigan
    0.74
     дописавши
    0.73
    lapsingToolbar
    0.72
    Activations Density 0.770%

    No Known Activations