© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 17-GEMMASCOPE-RES-16K
    11. 679
    Prev
    Next
    INDEX
    Explanations

    negative values or indications of invalid settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -
    -0.83
    2
    -0.80
    1
    -0.77
    ,
    -0.72
    D
    -0.71
    3
    -0.70
    5
    -0.69
    T
    -0.69
    ly
    -0.69
    6
    -0.68
    POSITIVE LOGITS
     Мексичка
    1.07
     Савезне
    1.06
    djangoproject
    1.00
     autorytatywna
    1.00
     للمعارف
    0.94
    uxxxx
    0.91
    GEBURTS
    0.90
     виправивши
    0.88
    LabelTagHelper
    0.87
    ########.
    0.87
    Activations Density 0.304%

    No Known Activations