© 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. 3-GEMMASCOPE-RES-16K
    11. 9255
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and formatting elements commonly used in academic writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.83
    #
    -0.74
    AsUp
    -0.73
    Hentet
    -0.72
     otomatig
    -0.72
     فريبيس
    -0.71
    InitVars
    -0.70
    دانشنامهٔ
    -0.68
    InstrumentedTest
    -0.67
     kaarangay
    -0.66
    POSITIVE LOGITS
    orescence
    0.51
     Bey
    0.49
    AddField
    0.47
     Cole
    0.47
    Signature
    0.44
     diplomat
    0.44
    anged
    0.43
    aced
    0.43
     tep
    0.43
    fordable
    0.42
    Activations Density 0.274%

    No Known Activations