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

    Neuronpedia

    Jacobian LensNEW
    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. 28-GEMMASCOPE-RES-16K
    11. 6261
    Prev
    Next
    INDEX
    Explanations

    references to racial and gender disparities in consumer behavior and workplace dynamics

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

    Decreased/increased, up/down arrows, statistical data

    np_acts-logits-general · gemini-2.0-flash

    quantity, increase, decrease, or separator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vœ
    -0.52
     beziehungs
    -0.51
    Demikian
    -0.49
      
    -0.45
     desertcart
    -0.44
     myſelf
    -0.44
     forthwith
    -0.43
     
    -0.42
    TokenNameLBRACE
    -0.42
     expediente
    -0.41
    POSITIVE LOGITS
     ->
    0.77
     -->
    0.73
     ppl
    0.72
     =>
    0.71
    !!
    0.68
     BUT
    0.65
     =
    0.64
    !!!
    0.64
     
    0.60
    -->
    0.60
    Activations Density 0.269%

    No Known Activations