© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 4801
    Prev
    Next
    INDEX
    Explanations

    numerical data related to programming and algorithmic functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éphane
    -0.78
    asuring
    -0.75
     '+':
    -0.73
     Parac
    -0.68
    iffance
    -0.67
    بوابة
    -0.66
     jScrollPane
    -0.65
     Swe
    -0.63
     Theſe
    -0.63
     Leven
    -0.62
    POSITIVE LOGITS
    MessageTagHelper
    0.72
    endphp
    0.69
    EndContext
    0.65
    ่านั้น
    0.65
    ⓧ
    0.62
     Jahrhunderts
    0.62
    sego
    0.61
     ninjago
    0.58
     SqlConnection
    0.57
    Vikings
    0.57
    Activations Density 0.341%

    No Known Activations