© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 931
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, their roles, and organizational mentions associated with them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NUMX
    -0.84
       
    -0.84
     CreateTagHelper
    -0.84
     iſt
    -0.83
     مشين
    -0.82
     quæ
    -0.79
     ainfi
    -0.78
     ;
    -0.78
    存于互联网档案馆
    -0.77
     inoxydable
    -0.76
    POSITIVE LOGITS
     etc
    0.93
    !!!!
    0.84
    !!!
    0.84
    !!
    0.81
    .....
    0.76
    ???
    0.74
    ....
    0.73
    !!!!!
    0.72
     thing
    0.72
     stuff
    0.71
    Activations Density 0.381%

    No Known Activations