© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 9515
    Prev
    Next
    INDEX
    Explanations

    questions and forms of address in conversational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     тебе
    -0.81
     твое
    -0.77
     тебя
    -0.77
     לך
    -0.77
     אתה
    -0.76
     твои
    -0.74
     deines
    -0.69
    אתה
    -0.69
     хочешь
    -0.69
     deiner
    -0.67
    POSITIVE LOGITS
     yourselves
    1.86
     jullie
    1.22
    你们
    1.16
     yall
    1.16
    你們
    1.16
     vocês
    1.14
    你们的
    0.96
     kalian
    0.92
     vostra
    0.88
     vuestra
    0.79
    Activations Density 0.107%

    No Known Activations