© 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. 15-GEMMASCOPE-RES-16K
    11. 4331
    Prev
    Next
    INDEX
    Explanations

    references to key individuals or entities within a 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
    ViewFeatures
    -0.77
     Arden
    -0.75
    .*")]
    -0.74
     Berna
    -0.74
    Parcelize
    -0.69
    stateProvider
    -0.68
     cref
    -0.67
    льки
    -0.67
     ")";
    -0.66
     dvs
    -0.66
    POSITIVE LOGITS
     Moos
    1.05
    Coo
    1.03
     Nook
    1.01
     Cooley
    0.96
     hoo
    0.95
    oob
    0.93
    Doo
    0.93
     Hoo
    0.91
     Dooley
    0.91
     hoops
    0.89
    Activations Density 0.163%

    No Known Activations