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. 105045
    Prev
    Next
    INDEX
    Explanations

    terms related to residential properties and real estate

    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
     Descubre
    -0.47
    Secretary
    -0.47
     Spinoza
    -0.46
     Japón
    -0.45
     Behör
    -0.44
    ógrafo
    -0.44
     Inscrivez
    -0.44
    MessageOf
    -0.44
     HISTORIA
    -0.44
     SECRETARY
    -0.44
    POSITIVE LOGITS
     Residential
    1.13
     residential
    1.12
    Residential
    1.10
    residential
    1.05
     سكانية
    0.77
    IDENTIAL
    0.74
     residencial
    0.73
    住宅
    0.65
     residences
    0.62
     home
    0.60
    Activations Density 0.002%

    No Known Activations