© 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. 20-GEMMASCOPE-RES-16K
    11. 14685
    Prev
    Next
    INDEX
    Explanations

    terms related to stealth, invisibility, and sneaky actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    invisibility or concealment

    np_acts-logits-general · gemini-2.0-flash

    invisibility and stealth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tonode
    -0.67
    TagMode
    -0.65
     nakalista
    -0.64
     initComponents
    -0.61
    ValueStyle
    -0.59
    principalTable
    -0.59
    ArgsConstructor
    -0.55
    MigrationBuilder
    -0.55
    queryInterface
    -0.55
    Personensuche
    -0.54
    POSITIVE LOGITS
     hidden
    2.58
    hidden
    2.23
     concealed
    2.21
     Hidden
    2.21
    Hidden
    2.17
     hiding
    2.14
     stealth
    2.06
     invisible
    1.98
     concealment
    1.92
     hide
    1.92
    Activations Density 0.621%

    No Known Activations