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. 2-GEMMASCOPE-RES-16K
    6. 13032
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.58
     intptr
    -0.51
     urgent
    -0.47
    uxxxx
    -0.46
    tagHelperRunner
    -0.46
     Sus
    -0.46
     erle
    -0.45
    urgent
    -0.45
    RefNanny
    -0.44
    WebElementEntity
    -0.44
    POSITIVE LOGITS
    BuildContext
    0.50
    relatively
    0.49
    final
    0.45
    kuuta
    0.42
     JAXBElement
    0.42
     ironically
    0.42
     hereinafter
    0.41
    TestingModule
    0.40
    djangoproject
    0.39
     productId
    0.38
    Activations Density 0.053%

    No Known Activations