© 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. 2-GEMMASCOPE-RES-16K
    6. 8333
    Prev
    Next
    INDEX
    Explanations

    references to the term "Bal" or variations of it, likely indicating a specific subject or entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    点此举报
    -0.53
     الحره
    -0.50
    DockStyle
    -0.48
     Mari
    -0.46
    RTLI
    -0.42
     raffredd
    -0.41
     pembaca
    -0.41
    éfonos
    -0.40
    发表于
    -0.40
    DropTable
    -0.40
    POSITIVE LOGITS
     Bal
    1.94
    Bal
    1.86
     bal
    1.75
    bal
    1.56
     BAL
    1.51
    BAL
    1.32
     Бал
    0.98
     Ballot
    0.93
     ballast
    0.92
     Balak
    0.91
    Activations Density 0.434%

    No Known Activations