© 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. 12-GEMMASCOPE-RES-16K
    11. 7905
    Prev
    Next
    INDEX
    Explanations

    elements related to mathematical expressions and matrices within technical or scientific texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 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
    Tikang
    -0.66
    Билгалдахарш
    -0.64
     odkazy
    -0.57
    ⓘ
    -0.47
     skai
    -0.44
     Wikipédia
    -0.44
    unos
    -0.43
     بیشتر
    -0.43
     felizes
    -0.43
     professora
    -0.42
    POSITIVE LOGITS
     فريبيس
    0.85
    UrlResolution
    0.82
    Personendaten
    0.70
    RegistryLite
    0.65
    ModelSerializer
    0.64
    Brainz
    0.64
    TemporalType
    0.63
    AccessorTable
    0.61
     endforeach
    0.60
     المعيارى
    0.60
    Activations Density 0.562%

    No Known Activations