Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12033
    Prev
    Next
    INDEX
    Explanations

    class definitions and their structures within programming code

    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
     Chwiliwch
    -0.57
    RTLR
    -0.56
     Roskov
    -0.50
    GOTREF
    -0.49
    NameInMap
    -0.49
    FunctionFlags
    -0.47
     různ
    -0.46
     rhestr
    -0.46
    Бахар
    -0.46
     autorytatywna
    -0.46
    POSITIVE LOGITS
     ujednoznacz
    0.47
    SpringBootTest
    0.43
     StatelessWidget
    0.41
    RenderAtEndOf
    0.39
    cửa
    0.38
     StatefulWidget
    0.36
    bootstrapcdn
    0.36
     Seminary
    0.35
     FontWeight
    0.35
    expandindo
    0.35
    Activations Density 0.276%

    No Known Activations