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

    Neuronpedia

    Jacobian LensNEW
    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. 0-GEMMASCOPE-RES-16K
    11. 6707
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "sum" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.64
    ChildScrollView
    -0.59
     ADO
    -0.54
    سطس
    -0.53
     surla
    -0.52
     inse
    -0.51
    PerformLayout
    -0.50
    tagHelper
    -0.49
    copg
    -0.49
    تقاوى
    -0.48
    POSITIVE LOGITS
    Unique
    0.62
    Sum
    0.59
     Sum
    0.59
     TAMBÉM
    0.57
     Summe
    0.56
    sum
    0.55
     Deb
    0.55
     suma
    0.54
     importado
    0.54
     Unique
    0.52
    Activations Density 0.289%

    No Known Activations