© 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. 12-GEMMASCOPE-RES-16K__L0-22
    6. 952
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gustav
    -0.77
    quirrel
    -0.75
    XtraEditors
    -0.75
    ukone
    -0.71
    orestation
    -0.71
    Gustav
    -0.71
     revisor
    -0.68
    logenetic
    -0.65
    lexia
    -0.64
    Dammit
    -0.64
    POSITIVE LOGITS
     offers
    1.72
     Offers
    1.63
     offer
    1.59
     Offer
    1.57
    offers
    1.55
     OFFER
    1.52
     offered
    1.49
    Offers
    1.48
     Offering
    1.47
     offering
    1.45
    Activations Density 0.027%

    No Known Activations