© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 21093
    Prev
    Next
    INDEX
    Explanations

    references to research support and acknowledgments

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

    author names and affiliations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSCoder
    -0.75
    posedge
    -0.61
    Obrázky
    -0.60
    yntaxException
    -0.57
    原始内容存档于
    -0.56
    principalColumn
    -0.56
     kasarigan
    -0.55
     الرياضيه
    -0.53
    المناصب
    -0.53
     otomatig
    -0.52
    POSITIVE LOGITS
    `,
    
    0.30
     cre
    0.30
     prov
    0.29
     Pré
    0.27
     жи
    0.27
    RTEE
    0.27
     Wyd
    0.26
     Cre
    0.25
    Biographie
    0.25
    matchCondition
    0.25
    Activations Density 0.001%

    No Known Activations