© 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. 16-GEMMASCOPE-RES-16K
    11. 5730
    Prev
    Next
    INDEX
    Explanations

    instances of reported speech, particularly direct quotations

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

    Attribution; precedes speech

    np_acts-logits-general · gemini-2.0-flash

    reporting speech

    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
     Мексичка
    -1.05
     ModelExpression
    -1.04
     EconPapers
    -0.96
    تقاوى
    -0.96
    writeField
    -0.89
    MessageOf
    -0.89
     الرياضيه
    -0.88
     AssemblyCompany
    -0.88
    AddTagHelper
    -0.85
     ComVisible
    -0.85
    POSITIVE LOGITS
    .
    0.79
     after
    0.46
     in
    0.46
     referring
    0.44
    hopped
    0.44
    Referències
    0.42
    cipit
    0.40
    minal
    0.40
    ↵↵
    0.40
    ocate
    0.39
    Activations Density 0.044%

    No Known Activations