© 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. 3-GEMMASCOPE-RES-16K
    11. 1683
    Prev
    Next
    INDEX
    Explanations

    different font specifications and properties

    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
    -------------</
    -0.48
    CADE
    -0.45
    uparrow
    -0.45
    engan
    -0.44
     dép
    -0.44
     puff
    -0.43
    ียด
    -0.43
    ieras
    -0.42
     cjs
    -0.42
    BILL
    -0.41
    POSITIVE LOGITS
    Font
    1.97
    ScopeManager
    1.28
     CreateTagHelper
    1.26
     Font
    1.20
    addGap
    1.07
    addPreferredGap
    1.06
    jspx
    1.05
    FONT
    0.98
     EconPapers
    0.97
    bootstrapcdn
    0.94
    Activations Density 0.006%

    No Known Activations