© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 10327
    Prev
    Next
    INDEX
    Explanations

    references to specific players and their medical conditions, especially related to the Achilles tendon

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wils
    -0.86
     McCullough
    -0.84
     Hodgson
    -0.74
    Varint
    -0.74
     Whyte
    -0.73
    gon
    -0.73
    dtd
    -0.72
    tek
    -0.71
    :#
    -0.71
    miary
    -0.71
    POSITIVE LOGITS
    AnchorStyles
    0.86
     useRef
    0.86
    artney
    0.79
    ^(@)
    0.79
    ysacchar
    0.78
     ***/
    0.78
     referenties
    0.78
    Наводи
    0.78
     Portail
    0.78
     MEG
    0.78
    Activations Density 1.778%

    No Known Activations