© 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. 3307
    Prev
    Next
    INDEX
    Explanations

    references to academic papers and research publications

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

    Research or academic papers

    np_acts-logits-general · gemini-2.0-flash

    working papers and technical reports

    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
    expandindo
    -1.05
    tvguidetime
    -0.79
    SaveChangesAsync
    -0.79
     cambiamento
    -0.78
    ाहरण
    -0.77
     change
    -0.76
    :✨
    -0.74
    SerializedName
    -0.73
    change
    -0.72
     viewDidLoad
    -0.71
    POSITIVE LOGITS
     document
    0.98
     report
    0.92
     Report
    0.85
     paper
    0.82
    Report
    0.78
     memo
    0.76
     Document
    0.76
     documento
    0.75
     publication
    0.75
     documents
    0.74
    Activations Density 0.368%

    No Known Activations