© 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. 2-GEMMASCOPE-RES-16K
    11. 1292
    Prev
    Next
    INDEX
    Explanations

    commands or indications to display or hide elements in a user interface

    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
    SBATCH
    -0.77
    Personendaten
    -0.72
    PhysRev
    -0.68
     OFDb
    -0.68
    migrationBuilder
    -0.66
    出版年
    -0.66
    zzleHttp
    -0.61
    AccessorTable
    -0.61
    TestingModule
    -0.60
    المكان
    -0.59
    POSITIVE LOGITS
    show
    1.09
    Show
    1.03
    SHOW
    0.84
     Show
    0.76
     SHOW
    0.75
     show
    0.63
     showing
    0.63
    Mostrar
    0.63
    显示
    0.57
    shows
    0.57
    Activations Density 0.213%

    No Known Activations