© 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. 16-GEMMASCOPE-RES-16K
    11. 15126
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to data and programming within a specific context

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

    LaTeX syntax

    np_acts-logits-general · gemini-2.0-flash

    doi, sec, extension, KPNA1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.78
     المعيارى
    -0.68
    :+:
    -0.67
    Personensuche
    -0.67
     disambiguazione
    -0.65
    EndGlobalSection
    -0.63
     snippetHide
    -0.62
    قایناقلار
    -0.62
    AnchorStyles
    -0.62
     ModelExpression
    -0.60
    POSITIVE LOGITS
     EconPapers
    0.54
     Kerja
    0.53
    UnifiedTopology
    0.52
    TestingModule
    0.50
    ゙
    0.48
    Ein
    0.47
     bénéfices
    0.46
    şil
    0.46
     isInitialized
    0.46
     eût
    0.46
    Activations Density 0.813%

    No Known Activations