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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 77244
    Prev
    Next
    INDEX
    Explanations

    terms related to durability and reliability of products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    parsedMessage
    -0.59
    OGND
    -0.58
    FunctionFlags
    -0.54
    addPreferredGap
    -0.52
    ChildIndex
    -0.51
     виправивши
    -0.50
    ValueStyle
    -0.50
    onedDateTime
    -0.49
     FetchType
    -0.48
     MediatR
    -0.46
    POSITIVE LOGITS
     durability
    0.79
     durable
    0.73
    Durability
    0.72
     sturdy
    0.72
    durable
    0.69
     Durability
    0.65
     Durable
    0.63
     Sturdy
    0.62
    Durable
    0.61
     toughness
    0.60
    Activations Density 0.009%

    No Known Activations