© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 3487
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "their."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Worten
    -0.58
    AxisAlignment
    -0.52
     Worte
    -0.51
    fjspx
    -0.49
    Clik
    -0.49
    oves
    -0.49
     Grüsse
    -0.48
    ます
    -0.47
     rewind
    -0.46
     typos
    -0.46
    POSITIVE LOGITS
    their
    0.96
    Their
    0.94
     their
    0.93
     Their
    0.84
     leur
    0.80
     jejich
    0.79
     THEIR
    0.75
     kanilang
    0.75
     nji
    0.72
     leurs
    0.71
    Activations Density 0.154%

    No Known Activations