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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 57299
    Prev
    Next
    INDEX
    Explanations

    references to negotiations or transactions involving people and their interactions

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

    Phrases describing requests, invitations, or communications where one person is asking another to take an action or provide information.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     étoit
    -0.42
     einsch
    -0.41
    határoz
    -0.40
     Geben
    -0.39
     leaſt
    -0.39
    tualmente
    -0.39
     nowadays
    -0.38
     idag
    -0.38
     maîtres
    -0.37
     secoli
    -0.37
    POSITIVE LOGITS
    ViewImports
    0.63
    uxxxx
    0.54
     betweenstory
    0.52
    
    0.50
     EconPapers
    0.46
     excru
    0.44
    ORAGE
    0.44
    antMatchers
    0.43
    ixote
    0.43
    tinyos
    0.43
    Activations Density 0.074%

    No Known Activations