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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 433
    Prev
    Next
    INDEX
    Explanations

    concerns related to email and data management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical descriptions of client-server connections and data transmission protocols.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InputTagHelper
    -0.32
    ࿐
    -0.32
     aprendiz
    -0.31
    reis
    -0.29
    ėmis
    -0.28
     ATTACH
    -0.28
     acompaña
    -0.28
     bañ
    -0.27
     ListTile
    -0.27
     conclusão
    -0.27
    POSITIVE LOGITS
     server
    2.16
     servers
    2.16
     Servers
    1.78
     Server
    1.75
     servidor
    1.63
    server
    1.62
    服务器
    1.61
     serveur
    1.60
    サーバー
    1.56
    Server
    1.55
    Activations Density 0.495%

    No Known Activations