Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 5909
    Prev
    Next
    INDEX
    Explanations

    chemical bonds and interactions in materials science contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 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
     szpital
    -0.38
    XmlRootElement
    -0.37
    retario
    -0.36
     amargo
    -0.36
    AddHtmlAttribute
    -0.36
     Kegiatan
    -0.35
    autorest
    -0.35
     hlas
    -0.35
     kehamilan
    -0.35
     voorwaarden
    -0.35
    POSITIVE LOGITS
     Majefty
    0.64
     CreateTagHelper
    0.61
    出版年
    0.60
     الحره
    0.58
    makeConstraints
    0.55
     Мексичка
    0.55
     auffi
    0.55
     NSCoder
    0.53
     Taktlose
    0.52
     ſche
    0.52
    Activations Density 0.634%

    No Known Activations