© 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. 34-GEMMASCOPE-RES-16K
    11. 11159
    Prev
    Next
    INDEX
    Explanations

    specific patterns and symbols that represent mathematical expressions, variables, and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TRIBUN
    -0.61
     незавершена
    -0.61
     "@/
    -0.52
    MigrationBuilder
    -0.49
    HasColumnName
    -0.49
    interopRequire
    -0.48
    ruptedException
    -0.48
     JAXBElement
    -0.47
    ⤹
    -0.47
    BeginContext
    -0.46
    POSITIVE LOGITS
    5
    1.13
     five
    0.93
     Five
    0.80
    five
    0.77
     cinco
    0.75
     пяти
    0.74
     fifth
    0.73
     fifty
    0.72
    ５
    0.71
     cinq
    0.71
    Activations Density 1.274%

    No Known Activations