© 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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 484
    Prev
    Next
    INDEX
    Explanations

    terms related to assets in a financial or resource management context

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

    Follows "Asset" or "ASS"

    np_acts-logits-general · gemini-2.0-flash

    asset or assumptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Redirection
    -0.63
     GenerationType
    -0.61
    usalem
    -0.55
    enerys
    -0.55
    IService
    -0.55
    ]._
    -0.55
    endphp
    -0.55
    orianCalendar
    -0.55
    hedral
    -0.53
    Ferdin
    -0.53
    POSITIVE LOGITS
    ConstraintMaker
    0.82
    ualaikum
    0.65
    "",
    
    0.62
    клопе
    0.61
     unknownFields
    0.60
    Географи
    0.60
    ={`/
    0.60
     KAY
    0.60
     '',
    
    0.60
    Попис
    0.59
    Activations Density 0.175%

    No Known Activations