© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 11226
    Prev
    Next
    INDEX
    Explanations

    phrases or contexts related to quantities or numbers of items or people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.65
     otomatig
    -0.57
    execSQL
    -0.57
    etheless
    -0.53
     StringIO
    -0.49
     jspb
    -0.48
     تكبرها
    -0.47
    rxjs
    -0.47
    tvguidetime
    -0.46
    DialogTitle
    -0.46
    POSITIVE LOGITS
    niająca
    0.56
    ⓧ
    0.56
    NumberOf
    0.56
     numberOf
    0.51
     Jack
    0.50
    numberOf
    0.50
    Jack
    0.47
     Thank
    0.44
     ComVisible
    0.39
     počet
    0.39
    Activations Density 0.054%

    No Known Activations