© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 9492
    Prev
    Next
    INDEX
    Explanations

    terms and components related to computer graphics, particularly in shader programming and rendering

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    RefNanny
    -0.46
    duras
    -0.39
    NewReader
    -0.39
    arrhea
    -0.37
    dera
    -0.37
     холоди
    -0.37
    igno
    -0.36
    Foreign
    -0.36
    listFiles
    -0.35
     démission
    -0.35
    POSITIVE LOGITS
    UniformLocation
    0.60
    AccessorTable
    0.59
    bootstrapcdn
    0.58
     AssemblyTitle
    0.57
    MigrationBuilder
    0.54
     '\\;'
    0.54
    outWeight
    0.53
     shader
    0.53
    AnimationsModule
    0.53
     Shader
    0.53
    Activations Density 0.129%

    No Known Activations