© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 15213
    Prev
    Next
    INDEX
    Explanations

    blocks of code or technical formatting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    r
    -0.58
    /}.
    -0.52
    ys
    -0.49
    rxjs
    -0.49
    mayacak
    -0.49
     بها
    -0.48
    aka
    -0.48
    is
    -0.48
    MethodManager
    -0.46
    ISE
    -0.46
    POSITIVE LOGITS
     typelib
    0.87
     Numerade
    0.84
    ThroughAttribute
    0.81
     Roskov
    0.78
    ^(@)
    0.75
     AssemblyCompany
    0.72
     Paglinawan
    0.70
     estekak
    0.68
    المناصب
    0.68
    ReusableCell
    0.68
    Activations Density 0.444%

    No Known Activations