© 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. 3618
    Prev
    Next
    INDEX
    Explanations

    references to business activities and transitions

    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
     pleinement
    -0.39
     throughout
    -0.38
     exclusion
    -0.38
     taba
    -0.38
    ướ
    -0.35
    Vidite
    -0.35
    Throughout
    -0.35
     Throughout
    -0.35
     additionally
    -0.35
     isNameExpr
    -0.34
    POSITIVE LOGITS
     altogether
    1.56
     entirely
    1.08
     forever
    1.02
     completely
    0.96
     Altogether
    0.96
     навсегда
    0.94
     permanently
    0.94
     kokona
    0.85
    forever
    0.83
    alto
    0.83
    Activations Density 0.732%

    No Known Activations