© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 10183
    Prev
    Next
    INDEX
    Explanations

    mentions of fairness or fair practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fromnode
    -0.50
    OleDb
    -0.45
    OBI
    -0.44
    thalene
    -0.42
    적으로
    -0.42
     GoogleFonts
    -0.41
     Rapp
    -0.41
     Pab
    -0.41
    ambique
    -0.41
     Normdatei
    -0.40
    POSITIVE LOGITS
     fair
    4.69
     Fair
    3.92
    fair
    3.91
    Fair
    3.84
     FAIR
    3.33
    FAIR
    3.25
     fairer
    2.84
     fairs
    2.81
     fairness
    2.64
     fairest
    2.61
    Activations Density 0.113%

    No Known Activations