Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 10891
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to server and client communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.47
     تضيفلها
    -0.38
    دانشنامهٔ
    -0.36
    mopolitan
    -0.34
     ucapnya
    -0.32
     kasarigan
    -0.32
     Residents
    -0.30
     RESID
    -0.30
     Bewohner
    -0.30
     ngành
    -0.30
    POSITIVE LOGITS
     server
    3.50
     Server
    2.95
     servers
    2.91
    server
    2.91
    Server
    2.70
     SERVER
    2.59
     serveur
    2.53
     Servers
    2.52
     servidor
    2.48
    服务器
    2.41
    Activations Density 0.571%

    No Known Activations