Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 57820
    Prev
    Next
    INDEX
    Explanations

    references to computer viruses and malware

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

    virus and viruses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prior
    -0.39
    prior
    -0.37
    rak
    -0.37
     PJ
    -0.36
    ritch
    -0.35
     Sco
    -0.35
     IOP
    -0.35
    回了
    -0.34
     detail
    -0.34
     Tau
    -0.33
    POSITIVE LOGITS
     viruses
    1.01
     vírus
    1.00
     virus
    0.99
    Virus
    0.98
     Virus
    0.93
     Viruses
    0.92
    virus
    0.80
    MLLoader
    0.73
     infect
    0.72
    viruses
    0.71
    Activations Density 0.048%

    No Known Activations