© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 957
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to programming, licensing, and data structures

    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
     
    -0.38
      
    -0.38
    ↵
    -0.36
        
    -0.33
     Sortiment
    -0.33
    -0.33
    enumi
    -0.33
    <em>
    -0.33
    )
    -0.33
    ↵↵
    -0.32
    POSITIVE LOGITS
     queſta
    1.15
    IUrlHelper
    0.95
     kaarangay
    0.92
    iſen
    0.92
    ſchaft
    0.91
    iffance
    0.90
    majánló
    0.89
     Roskov
    0.88
    ſcher
    0.88
    ſchen
    0.87
    Activations Density 1.102%

    No Known Activations