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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15931
    Prev
    Next
    INDEX
    Explanations

    terms related to rental agreements and evictions

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    XtraEditors
    -0.45
     وتسجيلات
    -0.40
     Obrador
    -0.40
     propOrder
    -0.40
    __':
    -0.40
     محفوظة
    -0.39
    oquia
    -0.39
    ngths
    -0.39
    iettivo
    -0.37
     bu
    -0.37
    POSITIVE LOGITS
     rents
    0.72
     landlord
    0.71
     rent
    0.69
     renters
    0.67
     tenant
    0.65
     Tenant
    0.64
     lease
    0.64
     Landlord
    0.63
     landlords
    0.63
     apartment
    0.63
    Activations Density 0.062%

    No Known Activations