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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 57321
    Prev
    Next
    INDEX
    Explanations

    relations and associations within the context of partnerships and organizational structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     ehre
    -0.28
     Second
    -0.28
     then
    -0.28
    <code>
    -0.27
     se
    -0.27
     light
    -0.27
     line
    -0.27
     #
    -0.27
     ST
    -0.27
     pop
    -0.26
    POSITIVE LOGITS
     للاسماء
    0.86
    LEncoder
    0.71
    StructEnd
    0.69
    ViewImports
    0.69
    脚注の使い方
    0.68
     themſelves
    0.65
    isContained
    0.65
     indígen
    0.63
    AccessorTable
    0.62
    LookAnd
    0.61
    Activations Density 0.018%

    No Known Activations