© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 5879
    Prev
    Next
    INDEX
    Explanations

    concepts related to depth and profound understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -1.16
    antMatchers
    -0.93
    ModelAdmin
    -0.90
    XmlAccessorType
    -0.87
     dévelo
    -0.86
    djangoproject
    -0.86
    RegistryLite
    -0.86
     ModelRenderer
    -0.85
    urlpatterns
    -0.85
    OGND
    -0.84
    POSITIVE LOGITS
     deep
    1.78
     DEEP
    1.73
     Deep
    1.67
    Deep
    1.53
    deep
    1.52
    DEEP
    1.47
     depth
    1.39
     deeper
    1.38
     deeply
    1.35
     depths
    1.33
    Activations Density 0.080%

    No Known Activations