© 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. 18-GEMMASCOPE-RES-16K
    11. 1809
    Prev
    Next
    INDEX
    Explanations

    references to events, particularly conferences and presentations

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

    Attendance or participation in something

    np_acts-logits-general · gemini-2.0-flash

    attendance and participation

    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
     nonatomic
    -0.68
    LoggerFactory
    -0.58
    ScopeManager
    -0.57
    eradish
    -0.54
    mybatisplus
    -0.54
    principalTable
    -0.54
     OFDb
    -0.53
     morgon
    -0.53
    ientôt
    -0.52
    oznam
    -0.52
    POSITIVE LOGITS
     attend
    1.93
     attending
    1.91
     participation
    1.75
     attends
    1.72
     participate
    1.67
     attendance
    1.64
     participating
    1.62
     participated
    1.61
     Attending
    1.58
     Attend
    1.57
    Activations Density 0.331%

    No Known Activations