© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14121
    Prev
    Next
    INDEX
    Explanations

    phrases related to authorship, contributions, and collaborative efforts in research studies

    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
     protoimpl
    -0.62
     gyhoeddwyd
    -0.49
    ChildScrollView
    -0.48
    CppMethod
    -0.47
    EDEFAULT
    -0.46
     ModelExpression
    -0.45
     chi̍t
    -0.43
    interopRequire
    -0.42
    parsedMessage
    -0.41
     arşivlendi
    -0.41
    POSITIVE LOGITS
     design
    3.88
    design
    3.39
     Design
    3.27
     DESIGN
    3.20
    Design
    3.19
     diseño
    3.13
     designs
    3.08
    设计
    3.03
    DESIGN
    3.00
     designing
    2.88
    Activations Density 1.245%

    No Known Activations