© 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-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 3792
    Prev
    Next
    INDEX
    Explanations

    variations of the word "create" and concepts related to building and developing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
     récentes
    -0.62
     récemment
    -0.60
    recent
    -0.59
     recentes
    -0.59
     RECENT
    -0.59
     perjuangan
    -0.57
     valmist
    -0.54
     Grecs
    -0.53
     evolução
    -0.53
     antiguo
    -0.53
    POSITIVE LOGITS
     lasting
    0.78
     new
    0.75
     prototypes
    0.69
     customized
    0.68
     relationships
    0.68
    lasting
    0.67
    TestingModule
    0.66
     workable
    0.66
     bonds
    0.66
     efficient
    0.66
    Activations Density 0.689%

    No Known Activations