© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 2604
    Prev
    Next
    INDEX
    Explanations

    events and actions related to violence and destruction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.59
     traite
    -0.53
     tightened
    -0.52
     tightening
    -0.51
    jspx
    -0.50
     Slip
    -0.50
     Réponses
    -0.49
     tighten
    -0.48
    increments
    -0.47
    signol
    -0.47
    POSITIVE LOGITS
     destruction
    2.08
     destroyed
    1.96
     Destruction
    1.74
     destroy
    1.71
    destruction
    1.64
     Destroy
    1.61
    Destruction
    1.61
     destroying
    1.59
     destru
    1.57
     wreckage
    1.56
    Activations Density 0.302%

    No Known Activations