© 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 - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 481
    Prev
    Next
    INDEX
    Explanations

    phrases related to commands in a programming or technical context

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

    Discord or Slack bot commands/messages

    np_acts-logits-general · gemini-2.0-flash

    slash commands, bot tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atguigu
    -0.62
    StructEnd
    -0.52
    MeasureSpec
    -0.51
     encantan
    -0.49
     xrange
    -0.49
     CHtml
    -0.47
     sulphuric
    -0.46
    InitVars
    -0.45
     relâche
    -0.45
     BoxFit
    -0.45
    POSITIVE LOGITS
     Discord
    0.84
     channel
    0.84
     Bot
    0.83
     bot
    0.82
     discord
    0.81
    Bot
    0.74
     Channel
    0.73
    Channel
    0.72
     channels
    0.72
    discord
    0.71
    Activations Density 0.212%

    No Known Activations