© 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. 24-GEMMASCOPE-RES-16K
    11. 10326
    Prev
    Next
    INDEX
    Explanations

    references to various objects and entities, especially in the context of their definitions and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding years

    np_acts-logits-general · gemini-2.0-flash

    names of things defined by properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     solcher
    -0.69
     متعلقه
    -0.67
    AntiForgeryToken
    -0.67
    脚注の使い方
    -0.65
     intitulée
    -0.62
     titulada
    -0.62
    Such
    -0.62
    +#+#
    -0.61
    ContentAsync
    -0.60
     abgerufen
    -0.58
    POSITIVE LOGITS
     originally
    1.12
     commonly
    0.93
     often
    0.90
     that
    0.88
     widely
    0.88
     famously
    0.86
     formerly
    0.82
     popular
    0.82
     currently
    0.82
    originally
    0.81
    Activations Density 0.414%

    No Known Activations