© 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. 12816
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significant increases or changes in numerical values or quantities

    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
     تضيفلها
    -0.57
     مُعرِّف
    -0.54
     CURIAM
    -0.50
     vapormax
    -0.49
    nice
    -0.49
    Detail
    -0.47
    debe
    -0.47
    ToPoint
    -0.47
     Loose
    -0.47
     bParam
    -0.46
    POSITIVE LOGITS
     drastically
    1.24
     increase
    1.22
     dramatically
    1.18
     increased
    1.08
     substantially
    1.05
     significantly
    1.02
     increases
    1.01
     Increase
    0.99
    increase
    0.98
     decrease
    0.98
    Activations Density 0.352%

    No Known Activations