© 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. 2-GEMMASCOPE-RES-16K
    11. 4390
    Prev
    Next
    INDEX
    Explanations

    negative mathematical expressions or operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    curities
    -0.45
     estr
    -0.44
     aikaa
    -0.43
    åga
    -0.42
    Lähteet
    -0.42
     Wirt
    -0.42
    ніше
    -0.41
    リエーション
    -0.41
    enschappen
    -0.41
    råd
    -0.41
    POSITIVE LOGITS
     (-
    2.33
    (-
    2.06
     (−
    1.98
     [-
    1.97
     $(-
    1.95
    =-
    1.82
     $-
    1.82
    [-
    1.77
    (−
    1.71
    }(-
    1.68
    Activations Density 0.393%

    No Known Activations