© 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. 17-GEMMASCOPE-RES-16K
    6. 515
    Prev
    Next
    INDEX
    Explanations

    presence of segmentation headers in the document

    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
     whichever
    -0.70
    <sup>
    -0.69
     such
    -0.64
     whatever
    -0.60
     Additionally
    -0.59
     herhangi
    -0.58
     suerte
    -0.58
    hichever
    -0.57
     either
    -0.57
      
    -0.57
    POSITIVE LOGITS
     autorytatywna
    0.95
    boldmath
    0.71
    ReusableCell
    0.68
     transférez
    0.68
     :
    0.67
    Havolalar
    0.63
    '".
    0.62
     '').
    0.62
    : 
    0.60
     AppModule
    0.60
    Activations Density 0.614%

    No Known Activations