© 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. 18-GEMMASCOPE-RES-16K
    11. 15252
    Prev
    Next
    INDEX
    Explanations

    components of code related to class and method definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     per
    -0.55
     --
    -0.54
     Ar
    -0.54
     un
    -0.54
     ar
    -0.52
     par
    -0.51
    mergeFrom
    -0.51
     Brown
    -0.49
     $
    -0.49
     box
    -0.48
    POSITIVE LOGITS
     getApplication
    0.97
    getApplication
    0.95
     itſelf
    0.94
     Efq
    0.83
     myſelf
    0.81
     Jefus
    0.80
    KEYCODE
    0.76
     deſt
    0.76
     ſmall
    0.75
     Chriſt
    0.74
    Activations Density 0.022%

    No Known Activations