© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 5735
    Prev
    Next
    INDEX
    Explanations

    elements related to labeling or inscriptions on various objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 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
    KommentareTeilen
    -1.07
     Efq
    -0.94
    ſelf
    -0.86
    المشاركات
    -0.86
     photolibrary
    -0.84
     $_"
    -0.84
    TagMode
    -0.84
     reaſon
    -0.84
     Houſe
    -0.82
     pleaſure
    -0.82
    POSITIVE LOGITS
     label
    0.81
     labels
    0.77
    label
    0.67
    labels
    0.58
     labelling
    0.57
     ver
    0.56
     labeling
    0.55
     sticker
    0.54
     Label
    0.54
    JLabel
    0.53
    Activations Density 0.267%

    No Known Activations