© 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. 5-GEMMASCOPE-RES-16K
    11. 15514
    Prev
    Next
    INDEX
    Explanations

    patterns of Unicode characters or symbols

    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
    expandindo
    -1.16
    webElement
    -1.04
    elemField
    -1.00
    ArrowToggle
    -0.99
    SourceChecksum
    -0.98
    webElementXpaths
    -0.97
    DockStyle
    -0.97
    OGND
    -0.95
    enterOuterAlt
    -0.94
     otomatig
    -0.94
    POSITIVE LOGITS
    u
    1.08
     u
    0.56
    \\[
    0.56
    CJK
    0.52
    สือ
    0.51
    U
    0.51
     Mc
    0.50
    يرا
    0.50
    ্
    0.49
    <0xD4>
    0.48
    Activations Density 0.069%

    No Known Activations