© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 11176
    Prev
    Next
    INDEX
    Explanations

    quantitative descriptors related to size, number, and volume variations in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.63
    #+#
    -0.59
    Искәрмәләр
    -0.58
     weakest
    -0.57
    qrstuvwxyz
    -0.57
    sidemargin
    -0.56
     تضيفلها
    -0.55
    তথ্যসূত্র
    -0.54
    nEnter
    -0.54
    AtIndex
    -0.53
    POSITIVE LOGITS
     (>
    1.34
     (~
    1.30
     (<
    1.06
     $(
    0.95
     (
    0.93
     ($
    0.90
     (.
    0.89
    (>
    0.83
     (−
    0.79
     ($\
    0.77
    Activations Density 0.838%

    No Known Activations