© 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. 22-GEMMASCOPE-RES-16K
    11. 7515
    Prev
    Next
    INDEX
    Explanations

    violence and physical confrontations

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

    Physical attacks, especially hitting

    np_acts-logits-general · gemini-2.0-flash

    physical impacts to the body

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.85
    tagHelperRunner
    -0.81
    IntoConstraints
    -0.76
    出版年
    -0.76
    setVerticalGroup
    -0.71
     IBOutlet
    -0.71
     שוליים
    -0.69
    脚注の使い方
    -0.69
    ChildScrollView
    -0.69
     MotionEvent
    -0.68
    POSITIVE LOGITS
     squarely
    0.72
     head
    0.61
     pleine
    0.60
     directly
    0.58
     hard
    0.57
     face
    0.55
     sekali
    0.53
     full
    0.52
     plein
    0.48
     resulting
    0.48
    Activations Density 0.150%

    No Known Activations