© 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. 20-GEMMASCOPE-RES-16K
    11. 878
    Prev
    Next
    INDEX
    Explanations

    details related to weapons, specifically swords and knives

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

    knives or sharp objects

    np_acts-logits-general · gemini-2.0-flash

    sharp knife or blade

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Lähteet
    -0.73
     EconPapers
    -0.59
    żesz
    -0.59
     referenties
    -0.57
     Bullock
    -0.56
    épendance
    -0.52
    Cyfeiriadau
    -0.52
    hoots
    -0.52
     Soares
    -0.52
     виправивши
    -0.51
    POSITIVE LOGITS
     blade
    1.44
     knife
    1.30
     blades
    1.26
     knives
    1.22
     Blade
    1.21
    Blade
    1.19
    blade
    1.14
     Knife
    1.13
    Knife
    1.10
     Blades
    1.09
    Activations Density 0.127%

    No Known Activations