© 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. 616
    Prev
    Next
    INDEX
    Explanations

    coding-related function definitions and file operations

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

    object creation and initialization in code.

    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
    XmlAccessorType
    -0.48
    ChildScrollView
    -0.35
     updateUser
    -0.35
    memoized
    -0.34
    updateUser
    -0.33
    詰
    -0.33
    coeur
    -0.33
    UPDATED
    -0.32
     ruine
    -0.32
     vendidos
    -0.32
    POSITIVE LOGITS
     creation
    1.82
     création
    1.62
     create
    1.59
     Creation
    1.55
     creating
    1.53
     creación
    1.52
     created
    1.51
     Create
    1.50
     Creating
    1.50
    创建
    1.48
    Activations Density 0.769%

    No Known Activations