© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4823
    Prev
    Next
    INDEX
    Explanations

    content that discusses regulations or guidelines related to violence in media

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

    Follows symbols such as $, {, or ="

    np_acts-logits-general · gemini-2.0-flash

    graphic content and violence

    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
    ]='\
    -0.67
    SOUNDBITE
    -0.62
    __':
    -0.59
     ilusión
    -0.58
    DMETHOD
    -0.57
    BeginInit
    -0.56
    TestBed
    -0.56
    oursquare
    -0.55
    __':
    -0.55
    DockStyle
    -0.54
    POSITIVE LOGITS
     offensive
    1.05
     nudity
    1.02
     objectionable
    1.02
     explicit
    0.98
     NSFW
    0.94
     vulgar
    0.93
     censored
    0.92
     gore
    0.90
     content
    0.88
     obscene
    0.87
    Activations Density 0.302%

    No Known Activations