© 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. 3076
    Prev
    Next
    INDEX
    Explanations

    punctuations and sentence boundaries

    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
    AddTagHelper
    -0.86
     nakalista
    -0.86
     houſe
    -0.83
     greateſt
    -0.82
     leſs
    -0.82
     pleaſure
    -0.81
     leaſt
    -0.81
     ſtate
    -0.79
     Jefus
    -0.78
    Personensuche
    -0.76
    POSITIVE LOGITS
     кӀ
    0.55
     хо
    0.52
     BoxFit
    0.51
    dafrika
    0.51
    География
    0.50
    chau
    0.50
     становника
    0.49
    errat
    0.48
    TagHelper
    0.47
     nó
    0.46
    Activations Density 0.265%

    No Known Activations