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. 40712
    Prev
    Next
    INDEX
    Explanations

    references to types of residential living arrangements and their associated attributes

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

    Words referring to human dwellings (homes, residences, housing) or their inhabitants (families, individuals, residents) in contexts describing living spaces and residential areas.

    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
    IDTH
    -0.40
     informaciones
    -0.40
    存于互联网档案馆
    -0.39
     vérit
    -0.36
     Autorizaciones
    -0.35
    ufficio
    -0.34
    DockStyle
    -0.34
    yelitis
    -0.34
    Мир
    -0.34
     strijd
    -0.34
    POSITIVE LOGITS
     household
    0.76
     households
    0.74
     homes
    0.73
     homeowner
    0.67
     homeowners
    0.66
     Household
    0.64
    family
    0.63
    Household
    0.62
    homes
    0.62
     householder
    0.62
    Activations Density 0.179%

    No Known Activations