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. 30424
    Prev
    Next
    INDEX
    Explanations

    quantitative data related to real estate, housing, and demographics

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

    housing and real estate

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ุทธ
    -0.32
    not
    -0.29
     môn
    -0.28
    brä
    -0.28
    extra
    -0.28
     paž
    -0.27
     praco
    -0.27
    XmlAccessType
    -0.27
    cross
    -0.26
     intro
    -0.26
    POSITIVE LOGITS
    GEBURTSDATUM
    1.09
     housing
    0.73
     dwellings
    0.73
     ujednoznacz
    0.73
     Housing
    0.71
    Housing
    0.68
     dwelling
    0.65
     residences
    0.65
    RegressionTest
    0.64
     apartments
    0.64
    Activations Density 0.071%

    No Known Activations