© 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. 2839
    Prev
    Next
    INDEX
    Explanations

    statistical data related to sports performance metrics

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

    NBA or hockey season/transactions

    np_acts-logits-general · gemini-2.0-flash

    hungry plaintiff lawyers

    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
     Students
    -0.60
    Students
    -0.60
     students
    -0.55
    students
    -0.54
    Campus
    -0.53
     Studenten
    -0.52
     Campus
    -0.52
     Graduates
    -0.52
    student
    -0.50
     alunos
    -0.50
    POSITIVE LOGITS
     itſelf
    0.90
     Theſe
    0.86
     houſe
    0.85
     Monfieur
    0.83
     Efq
    0.81
     franchise
    0.81
     Anſ
    0.81
     Eſ
    0.81
     Houſe
    0.80
    windowFixed
    0.77
    Activations Density 0.385%

    No Known Activations