© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 4802
    Prev
    Next
    INDEX
    Explanations

    instances of violence or assassination

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

    Torture, murder, and execution

    np_acts-logits-general · gemini-2.0-flash

    acts of cruelty and death

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     विश्वसनीयता
    -0.63
     validated
    -0.56
     Nestor
    -0.55
    URLException
    -0.54
     casó
    -0.53
     qualifying
    -0.53
    emption
    -0.52
     kritik
    -0.51
    mpotent
    -0.51
     चीज़ों
    -0.50
    POSITIVE LOGITS
     torture
    0.80
     cruel
    0.66
     Torture
    0.66
     tort
    0.61
     tortura
    0.60
     cruelly
    0.58
     brutal
    0.58
     tortured
    0.58
     merciless
    0.57
     cruelty
    0.57
    Activations Density 0.343%

    No Known Activations