© 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. 4797
    Prev
    Next
    INDEX
    Explanations

    terms related to familial roles and relationships

    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
     AssemblyCompany
    -0.30
     effectively
    -0.27
     St
    -0.27
    1
    -0.24
    ↵
    -0.24
    робнее
    -0.24
     p
    -0.23
                                
    -0.23
                               
    -0.23
     E
    -0.23
    POSITIVE LOGITS
     ſeine
    0.86
     queſta
    0.81
     zuſammen
    0.81
     мәкал
    0.78
    🜲
    0.78
    ðsíða
    0.77
     beſch
    0.77
     dieſer
    0.77
    <unused43>
    0.77
    <unused41>
    0.76
    Activations Density 0.594%

    No Known Activations