© 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. 35-GEMMASCOPE-RES-16K
    11. 13964
    Prev
    Next
    INDEX
    Explanations

    phrases describing a player's capability and performance in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WEBPACK
    -0.44
     campeão
    -0.35
    IRQn
    -0.33
     propOrder
    -0.33
     Design
    -0.32
     chois
    -0.32
     Hochsch
    -0.31
     campeones
    -0.31
     scored
    -0.31
     zobac
    -0.31
    POSITIVE LOGITS
     Infórmanos
    0.68
    migrationBuilder
    0.67
     intang
    0.64
    AddTagHelper
    0.63
     betweenstory
    0.61
     mojo
    0.56
    StructEnd
    0.56
     protoimpl
    0.56
     informée
    0.55
    queryInterface
    0.55
    Activations Density 0.195%

    No Known Activations