© 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. 34-GEMMASCOPE-RES-16K
    11. 10849
    Prev
    Next
    INDEX
    Explanations

    concepts related to familial relationships and paternity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addGap
    -0.28
    lą
    -0.27
    clientY
    -0.26
    月号
    -0.26
    campista
    -0.26
    getOutputStream
    -0.26
     MenuView
    -0.26
    ग्री
    -0.25
     sebou
    -0.25
    loem
    -0.25
    POSITIVE LOGITS
     father
    3.41
     Father
    2.94
    father
    2.91
    Father
    2.89
     fathers
    2.88
     dad
    2.84
     Dad
    2.61
     daddy
    2.55
    Dad
    2.52
     père
    2.44
    Activations Density 0.495%

    No Known Activations