© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 9811
    Prev
    Next
    INDEX
    Explanations

    instances of the word "his" and variations thereof, indicating a focus on male subjects or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.66
    ✨:
    -0.51
     فريبيس
    -0.49
    Hauptartikel
    -0.49
     Hän
    -0.46
    aap
    -0.46
    kPa
    -0.44
     uVar
    -0.44
    MENAFN
    -0.44
    axel
    -0.44
    POSITIVE LOGITS
     whose
    0.57
     whoſe
    0.56
     whofe
    0.55
    whose
    0.54
     cuja
    0.47
     cuyo
    0.46
    Whose
    0.43
     Económica
    0.42
     cujo
    0.42
     cuya
    0.41
    Activations Density 0.373%

    No Known Activations