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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 118915
    Prev
    Next
    INDEX
    Explanations

    references to Kubernetes and WebGL

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

    Kubernetes, WebGL, PhysRevLett

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    flashdata
    -0.50
    TagHelper
    -0.34
    #
    -0.33
    FromArgb
    -0.31
    UpInside
    -0.30
    ồi
    -0.29
    Cash
    -0.29
    <!--[
    -0.29
    Slf
    -0.28
     Ersten
    -0.28
    POSITIVE LOGITS
     Kubernetes
    2.19
    Kubernetes
    1.78
     kubernetes
    1.69
    kubernetes
    1.64
    kube
    0.85
     kube
    0.84
    ubernetes
    0.83
    Kube
    0.79
    kubectl
    0.76
    apimachinery
    0.73
    Activations Density 0.002%

    No Known Activations