© 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. 31-GEMMASCOPE-RES-16K
    11. 6208
    Prev
    Next
    INDEX
    Explanations

    references to the treatment of individuals, particularly regarding issues of racial discrimination and equity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases describing how people were treated, particularly in contexts involving differential or comparative treatment.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.57
     AssemblyCulture
    -0.56
    JspWriter
    -0.55
    HideFlags
    -0.52
    GEBURTSDATUM
    -0.50
    writeFieldEnd
    -0.48
    تقاوى
    -0.46
     ſte
    -0.45
     Италијани
    -0.45
    rungsseite
    -0.45
    POSITIVE LOGITS
     differently
    1.05
     like
    0.79
     very
    0.70
     extremely
    0.69
     according
    0.62
     fairly
    0.61
     poorly
    0.58
     decently
    0.58
     exceptionally
    0.57
     accordingly
    0.56
    Activations Density 0.743%

    No Known Activations