© 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. 229
    Prev
    Next
    INDEX
    Explanations

    references to violent crimes and incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Numerade
    -0.66
    TagMode
    -0.61
     plaisir
    -0.57
     كومونز
    -0.52
     سكانية
    -0.52
     Biar
    -0.50
    internalType
    -0.49
     adop
    -0.49
     Miscell
    -0.49
    ее
    -0.48
    POSITIVE LOGITS
     attacks
    0.77
     attack
    0.76
     robbery
    0.73
    setViewportView
    0.66
    Attacks
    0.65
     robberies
    0.62
     crime
    0.60
     serangan
    0.59
     robbers
    0.59
    attacks
    0.59
    Activations Density 0.262%

    No Known Activations