© 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. 23-GEMMASCOPE-RES-16K
    11. 2218
    Prev
    Next
    INDEX
    Explanations

    references to specific technological products and brands, particularly software and devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    期刊论文
    -0.42
     pinulongan
    -0.41
     NSCoder
    -0.30
     coger
    -0.30
     dniu
    -0.29
     volon
    -0.29
     pojaw
    -0.29
    mode
    -0.29
     ocze
    -0.29
    อยู่
    -0.28
    POSITIVE LOGITS
    Personensuche
    0.68
    HasForeignKey
    0.58
     Мексичка
    0.58
     AssemblyCulture
    0.57
    出版年
    0.55
     oprot
    0.54
    ValueStyle
    0.54
    ViewFeatures
    0.53
    complexContent
    0.52
    zzleHttp
    0.52
    Activations Density 0.655%

    No Known Activations