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. 32-GEMMASCOPE-RES-131K
    6. 129936
    Prev
    Next
    INDEX
    Explanations

    references to gatherings and events that involve food and social interaction

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

    events and services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.32.hook_resid_post
    Hook Layer
    32
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.73
    StructEnd
    -0.70
     Roskov
    -0.69
    ConstraintMaker
    -0.69
    -------------</
    -0.66
    ंदीखरीदारी
    -0.65
     Administrativna
    -0.63
    IsMutable
    -0.62
    ----</
    -0.60
    exitRule
    -0.60
    POSITIVE LOGITS
     throughout
    0.71
     attendees
    0.65
     courtesy
    0.62
    Throughout
    0.61
     provided
    0.61
     providing
    0.60
     featuring
    0.60
     cortesía
    0.59
     sponsored
    0.59
     starting
    0.59
    Activations Density 0.013%

    No Known Activations