© 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. 10-GEMMASCOPE-RES-16K
    6. 8348
    Prev
    Next
    INDEX
    Explanations

    numerical values or references to statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     himſelf
    -0.56
    iſen
    -0.54
     uLocal
    -0.53
    iſter
    -0.53
    moveToFirst
    -0.52
     ſur
    -0.52
    gjenge
    -0.51
     myſelf
    -0.50
     itſelf
    -0.50
    Ellie
    -0.49
    POSITIVE LOGITS
    9
    1.33
     ninety
    0.81
    9
    0.79
    ৯
    0.75
    ۹
    0.74
     Ninety
    0.72
     nine
    0.68
     Ninth
    0.66
     ninth
    0.66
     девя
    0.64
    Activations Density 0.671%

    No Known Activations