© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 2538
    Prev
    Next
    INDEX
    Explanations

    references to concepts of completeness or totality in relation to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.58
     виправивши
    -0.41
    ponses
    -0.41
     ویکی‌پدیای
    -0.41
     فريبيس
    -0.40
    مقاله
    -0.40
     سكانية
    -0.40
     وتسجيلات
    -0.40
    SerializedName
    -0.40
     typelib
    -0.38
    POSITIVE LOGITS
     extent
    1.63
    extent
    1.27
     detriment
    1.11
     degree
    1.10
     Extent
    1.06
     fullest
    0.88
     tune
    0.88
    degree
    0.85
    Extent
    0.85
     hilt
    0.83
    Activations Density 0.322%

    No Known Activations