© 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
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 15458
    Prev
    Next
    INDEX
    Explanations

    financial statistics and data related to household income

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.56
    InitVars
    -0.53
     pinulongan
    -0.51
    mybatisplus
    -0.47
    ༘
    -0.47
     Meksiku
    -0.47
     YellowPages
    -0.46
     AssemblyTitle
    -0.46
    migrationBuilder
    -0.45
     Autorizaciones
    -0.44
    POSITIVE LOGITS
     income
    2.39
    income
    2.02
     Income
    1.96
    Income
    1.91
     INCOME
    1.86
     incomes
    1.79
     earnings
    1.47
    收入
    1.42
     earning
    1.38
     Einkommen
    1.33
    Activations Density 0.447%

    No Known Activations