© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13623
    Prev
    Next
    INDEX
    Explanations

    elements related to stealth and evasion

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

    Invisibility or secrecy

    np_acts-logits-general · gemini-2.0-flash

    concealment, secrecy, privacy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    OGND
    -0.58
    Autoritní
    -0.55
    migrationBuilder
    -0.50
    MessageOf
    -0.48
     AssemblyCompany
    -0.47
    AutoField
    -0.47
    clerView
    -0.45
    LabelTagHelper
    -0.45
     actionMode
    -0.44
    TagMode
    -0.44
    POSITIVE LOGITS
     concealment
    0.88
     hiding
    0.84
     privacy
    0.81
     hidden
    0.81
     hide
    0.78
     secrecy
    0.77
    Hiding
    0.76
     concealing
    0.76
     concealed
    0.75
     conceal
    0.73
    Activations Density 0.562%

    No Known Activations