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. 114949
    Prev
    Next
    INDEX
    Explanations

    references to online discussion threads and posts

    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
    GOTREF
    -0.47
    AddTagHelper
    -0.47
    ContextCompat
    -0.45
     kaynağından
    -0.42
     CURIAM
    -0.42
     saira
    -0.41
     transitional
    -0.40
    corporate
    -0.40
    حوالہ
    -0.40
    DataAnnotations
    -0.39
    POSITIVE LOGITS
     thread
    0.75
     topic
    0.61
     threads
    0.60
    athread
    0.54
    thread
    0.54
     hilos
    0.52
     Thread
    0.50
     THREAD
    0.48
     discussion
    0.47
    ChildScrollView
    0.47
    Activations Density 0.013%

    No Known Activations