© 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. 37-GEMMASCOPE-RES-16K
    11. 5064
    Prev
    Next
    INDEX
    Explanations

    elements related to authorship and contributions 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 @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    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
    -0.51
    ChildScrollView
    -0.48
     gyhoeddwyd
    -0.44
     bVar
    -0.43
    CppMethod
    -0.42
     strconv
    -0.39
     ModelExpression
    -0.38
    EDEFAULT
    -0.38
    writeFieldEnd
    -0.37
    interopRequire
    -0.37
    POSITIVE LOGITS
     design
    3.80
    design
    3.31
     Design
    3.20
     DESIGN
    3.14
    Design
    3.14
     diseño
    3.11
     designs
    3.09
    设计
    3.00
    DESIGN
    2.95
     desain
    2.88
    Activations Density 1.058%

    No Known Activations