© 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. 20-GEMMASCOPE-RES-16K
    11. 11368
    Prev
    Next
    INDEX
    Explanations

    references to historical events and changes in business or economic conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.59
     فريبيس
    -0.57
    yntaxException
    -0.56
    AISSEE
    -0.56
     theyre
    -0.53
    ﹧
    -0.52
     Gd
    -0.52
    
    -0.52
    ⸒
    -0.52
     pleaſure
    -0.51
    POSITIVE LOGITS
     eventually
    0.53
     became
    0.52
     then
    0.47
    Eventually
    0.44
     later
    0.43
     soon
    0.43
     तब
    0.43
     inicialmente
    0.42
     thereafter
    0.41
     until
    0.41
    Activations Density 0.434%

    No Known Activations