© 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-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 5888
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate factors influencing decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CanadaChoose
    -0.41
    上
    -0.34
    内外
    -0.33
    oredCriteria
    -0.32
    APON
    -0.32
     amid
    -0.32
    RefNanny
    -0.32
     nữa
    -0.32
     favorite
    -0.32
    竟
    -0.32
    POSITIVE LOGITS
     whereas
    2.92
    whereas
    2.75
     Whereas
    2.59
    Whereas
    2.56
     sedangkan
    1.98
     natomiast
    1.88
     conversely
    1.84
     tandis
    1.82
     Conversely
    1.80
     hingegen
    1.77
    Activations Density 0.880%

    No Known Activations