© 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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12952
    Prev
    Next
    INDEX
    Explanations

    keywords related to financial responsibilities and maintenance obligations in property management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    bav
    -0.30
    RTCF
    -0.30
    탕
    -0.28
     sim
    -0.27
     arah
    -0.27
    package
    -0.27
    0
    -0.27
    授
    -0.26
    RemoveField
    -0.26
     publish
    -0.26
    POSITIVE LOGITS
     asbestos
    0.68
     repairing
    0.68
    parsedMessage
    0.68
     repairs
    0.67
    MigrationBuilder
    0.66
    Cyfarwyddwr
    0.64
     invokingState
    0.64
    bestos
    0.63
     $_"
    0.63
    SequentialGroup
    0.63
    Activations Density 0.132%

    No Known Activations