© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1310
    Prev
    Next
    INDEX
    Explanations

    graphic depictions of violence or injury

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

    references to violent or gory imagery involving dismemberment and body parts

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

    severing, decapitation, amputation

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    fjspx
    -0.83
    IonicModule
    -0.81
    sizeCache
    -0.76
    الحياه
    -0.75
     surla
    -0.75
     Theſe
    -0.73
    styleable
    -0.73
     itſelf
    -0.70
     themſelves
    -0.69
     myſelf
    -0.69
    POSITIVE LOGITS
     severed
    1.10
     decap
    0.93
     amput
    0.90
     amputation
    0.87
     limb
    0.79
    decap
    0.78
     limbs
    0.75
    sever
    0.75
     head
    0.74
     sever
    0.73
    Activations Density 0.092%

    No Known Activations