© 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. 24-GEMMASCOPE-RES-16K
    11. 6717
    Prev
    Next
    INDEX
    Explanations

    phrases related to internet content regulation and moderation practices

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

    terms related to internet governance and content regulation

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

    Comment moderation and account suspensions

    np_acts-logits-general · gemini-2.0-flash

    banned, suspended, deleted content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    舺
    -0.73
     Biôgrafia
    -0.59
     sánh
    -0.57
    KommentareTeilen
    -0.53
     stethoscope
    -0.52
     aérea
    -0.50
    ngrx
    -0.49
     telefónica
    -0.48
    tabular
    -0.47
    ]='\
    -0.46
    POSITIVE LOGITS
     moderation
    1.18
     blocked
    1.16
     banning
    1.10
     banned
    1.09
     blocking
    1.07
     ban
    1.07
     moderators
    1.06
     moderator
    1.05
     Moder
    1.02
     bans
    1.00
    Activations Density 0.349%

    No Known Activations