© 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. 21-GEMMASCOPE-RES-16K
    11. 10629
    Prev
    Next
    INDEX
    Explanations

    elements related to file handling and scripting in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.43
    typeorm
    -0.36
    RequiresApi
    -0.30
    يميديا
    -0.30
    SpringRunner
    -0.29
     industriales
    -0.28
     adecuadas
    -0.28
    BrowserModule
    -0.28
     oppervlak
    -0.28
    MigrationBuilder
    -0.28
    POSITIVE LOGITS
    twimg
    0.56
    ніципа
    0.53
    saraba
    0.50
    olescence
    0.45
    ennifer
    0.45
     Coon
    0.45
     Autorisations
    0.45
     tiguan
    0.44
    InputBorder
    0.44
    kolle
    0.44
    Activations Density 0.369%

    No Known Activations