© 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. 1-GEMMASCOPE-RES-16K
    11. 2815
    Prev
    Next
    INDEX
    Explanations

    terms related to exclusion and exclusionary practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    styleType
    -0.52
    DockStyle
    -0.40
    WriteAttribute
    -0.39
     Eg
    -0.38
    Ин
    -0.35
    jgl
    -0.34
     reas
    -0.34
    市
    -0.33
    GIH
    -0.33
    extAlignment
    -0.33
    POSITIVE LOGITS
    Expanded
    0.77
     excludes
    0.73
     whoever
    0.70
    Hvem
    0.70
     exclude
    0.70
     excluded
    0.69
    Who
    0.68
     expansion
    0.68
     Quien
    0.68
     Siapa
    0.67
    Activations Density 0.236%

    No Known Activations