© 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
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 8561
    Prev
    Next
    INDEX
    Explanations

    actions associated with stealth and thievery

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

    Uncommon or unique words

    np_acts-logits-general · gemini-2.0-flash

    invisibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Infór
    -0.66
     financeira
    -0.57
     mijne
    -0.57
     wireType
    -0.54
    __':
    -0.54
    RectangleBorder
    -0.52
    __':
    -0.52
     zijne
    -0.52
    gdx
    -0.50
     acrí
    -0.50
    POSITIVE LOGITS
     stealth
    1.26
     sneaking
    1.16
     sneak
    1.15
    stealth
    1.02
     sneaky
    0.94
     sne
    0.94
     Stealth
    0.91
    sneak
    0.90
     secretly
    0.88
     undetected
    0.88
    Activations Density 0.276%

    No Known Activations