© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1468
    Prev
    Next
    INDEX
    Explanations

    terms related to car financing and repayment

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

    Mortgages, loans, and repayments

    np_acts-logits-general · gemini-2.0-flash

    monthly repayment period

    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-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
    Chham
    -0.41
    ngrx
    -0.39
     NgModule
    -0.38
    virt
    -0.38
    measure
    -0.38
    transQ
    -0.35
    detect
    -0.35
     stench
    -0.35
     VIOL
    -0.34
     mackerel
    -0.34
    POSITIVE LOGITS
     mortgage
    0.62
    mortgage
    0.52
     Mortgage
    0.50
     monthly
    0.48
     lease
    0.48
    principalTable
    0.47
    Werde
    0.46
     queſta
    0.46
    Lycka
    0.46
    träd
    0.46
    Activations Density 0.156%

    No Known Activations