© 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. 12-GEMMASCOPE-RES-16K
    11. 15004
    Prev
    Next
    INDEX
    Explanations

    references to family relationships and connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CURLOPT
    -0.50
     noDo
    -0.44
     pitch
    -0.44
     Richt
    -0.41
    swire
    -0.40
     vocale
    -0.39
     Lightning
    -0.39
    phro
    -0.39
    pitch
    -0.39
     Vort
    -0.38
    POSITIVE LOGITS
    Family
    1.73
     family
    1.72
    family
    1.64
     Family
    1.63
     FAMILY
    1.55
    FAMILY
    1.52
    Families
    1.26
     famille
    1.24
     Families
    1.24
     families
    1.22
    Activations Density 0.088%

    No Known Activations