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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 13121
    Prev
    Next
    INDEX
    Explanations

    roles and contributions of individuals in a research study

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    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
    -0.59
     gyhoeddwyd
    -0.50
     arşivlendi
    -0.49
     ModelExpression
    -0.44
     strconv
    -0.44
    ChildScrollView
    -0.44
     otomatig
    -0.43
    interopRequire
    -0.43
     bVar
    -0.42
    MigrationBuilder
    -0.41
    POSITIVE LOGITS
     design
    3.69
    design
    3.22
     Design
    3.05
     DESIGN
    3.03
     diseño
    2.97
    Design
    2.97
     designs
    2.89
    设计
    2.89
    DESIGN
    2.84
     desain
    2.77
    Activations Density 0.834%

    No Known Activations