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. 91564
    Prev
    Next
    INDEX
    Explanations

    references to single-family homes and related housing characteristics

    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
     Polda
    -0.40
    łąd
    -0.39
    asinya
    -0.38
     tiens
    -0.37
    ölker
    -0.36
    TRAILING
    -0.35
    ijų
    -0.35
    züglich
    -0.34
     Rhein
    -0.34
     EconPapers
    -0.34
    POSITIVE LOGITS
    DoubleQuotes
    0.62
     residential
    0.62
    residential
    0.61
    Diweddarwch
    0.59
    ValueStyle
    0.58
    Residential
    0.56
     Residential
    0.56
    UrlResolution
    0.55
     suburban
    0.54
     residences
    0.54
    Activations Density 0.002%

    No Known Activations