© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 3655
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical constructs or structures, specifically in linear algebra or vector spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ToBounds
    -0.58
    zają
    -0.56
     Chara
    -0.53
    NUMX
    -0.53
     Fathers
    -0.50
    testng
    -0.50
     SMI
    -0.50
    Figs
    -0.50
    Figura
    -0.49
     OnInit
    -0.48
    POSITIVE LOGITS
    SharedDtor
    0.75
     يتيمه
    0.66
     autorytatywna
    0.62
    quelize
    0.62
     урна
    0.60
    otimes
    0.59
     переписи
    0.58
    hassee
    0.56
    épendance
    0.55
     Italijanski
    0.54
    Activations Density 1.325%

    No Known Activations