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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7055
    Prev
    Next
    INDEX
    Explanations

    concepts related to financial assistance and eligibility criteria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adalajara
    -0.37
     häm
    -0.34
     Treue
    -0.34
     positivo
    -0.33
     positivas
    -0.33
     fieles
    -0.31
     Einheit
    -0.31
     rafraî
    -0.31
    trà
    -0.31
     personalizado
    -0.31
    POSITIVE LOGITS
     poverty
    0.63
     income
    0.61
    poverty
    0.60
    Poverty
    0.60
    QMetaType
    0.58
     incomes
    0.57
    CppMethod
    0.57
     Income
    0.56
     Poverty
    0.56
    Income
    0.55
    Activations Density 0.280%

    No Known Activations