© 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-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 12889
    Prev
    Next
    INDEX
    Explanations

    special tokens indicating the start or end of sections within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Eastwood
    -0.67
     calendriers
    -0.67
    complexType
    -0.64
     ivelany
    -0.64
     AppBundle
    -0.58
    velvet
    -0.57
    ````
    -0.56
    tvguidetime
    -0.56
    考えて
    -0.56
    bė
    -0.56
    POSITIVE LOGITS
    \
    0.76
    #\
    0.72
     Rhy
    0.69
    ็จ
    0.68
     Kier
    0.68
     rospy
    0.67
     geodes
    0.66
     Jok
    0.66
     تضيفلها
    0.65
    पया
    0.65
    Activations Density 0.010%

    No Known Activations