© 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-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 11320
    Prev
    Next
    INDEX
    Explanations

    references to security vulnerabilities and concerns related to hacking and information safety

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

    The neuron detects cybersecurity and hacking–related content, activating on words and token fragments about hackers, malware/compromises, security (and related project/path fragments like OWASP/AppSensor).

    oai_token-act-pair · gpt-5-miniTriggered by @phamvanluong2003
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.66
     ArrayAdapter
    -0.65
    ArgsConstructor
    -0.62
    StoryboardSegue
    -0.59
    таратура
    -0.57
     {?>
    -0.56
    MessageTagHelper
    -0.54
     createSprite
    -0.52
     mxArray
    -0.52
    esModule
    -0.51
    POSITIVE LOGITS
     cybersecurity
    0.91
     cyber
    0.89
     Cyber
    0.86
     hacker
    0.83
     Malware
    0.76
    Cyber
    0.75
     vulnerabilities
    0.74
     hackers
    0.73
     malware
    0.73
     Cybersecurity
    0.71
    Activations Density 0.308%

    No Known Activations