© 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. 23-GEMMASCOPE-RES-16K
    11. 9673
    Prev
    Next
    INDEX
    Explanations

    phrases denoting continuous action or behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.64
    StoryboardSegue
    -0.51
    WriteTagHelper
    -0.50
    tableFuture
    -0.46
    AutoField
    -0.45
     mouseClicked
    -0.45
    #
    -0.43
    colta
    -0.43
    AnimationsModule
    -0.42
     intptr
    -0.42
    POSITIVE LOGITS
     constantly
    0.82
     constantemente
    0.74
     continually
    0.73
    不斷
    0.71
    不断的
    0.70
    不断
    0.69
     continuously
    0.68
     continuamente
    0.66
     constamment
    0.61
     CONSTANT
    0.59
    Activations Density 0.349%

    No Known Activations