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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 113363
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to servers and their configurations

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

    servers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.52
    AnchorTagHelper
    -0.48
    YourGuide
    -0.47
    findpost
    -0.45
    السكان
    -0.41
    ApiOperation
    -0.41
    Brands
    -0.40
    SPR
    -0.39
    ypeł
    -0.38
    TextWatcher
    -0.38
    POSITIVE LOGITS
     servers
    0.76
     server
    0.66
     Servers
    0.61
     computers
    0.59
     Server
    0.56
    sidemargin
    0.52
    服务器
    0.52
    サーバー
    0.51
     serveur
    0.51
     servidores
    0.50
    Activations Density 0.031%

    No Known Activations