© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 6481
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and operators related to equations

    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
     Infórmanos
    -0.54
    include
    -0.51
    cotch
    -0.51
     posiad
    -0.47
    郝
    -0.44
    iwa
    -0.43
    ApiProperty
    -0.42
     розви
    -0.42
     rodz
    -0.41
    ham
    -0.41
    POSITIVE LOGITS
     Z
    0.96
    Z
    0.92
     Zat
    0.88
     Zinc
    0.86
    getZ
    0.86
     Zoning
    0.84
     Zin
    0.82
     ZONE
    0.82
     Zink
    0.82
     ZAP
    0.81
    Activations Density 0.480%

    No Known Activations