© 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. 5696
    Prev
    Next
    INDEX
    Explanations

    quantitative data related to patient outcomes and response rates in medical studies

    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
    дото
    -0.56
     تضيفلها
    -0.49
     للمعارف
    -0.48
    job
    -0.44
    +#+
    -0.43
     JOB
    -0.41
    HostException
    -0.40
    or
    -0.40
    oto
    -0.40
    كويكب
    -0.40
    POSITIVE LOGITS
     autorytatywna
    0.78
    TagMode
    0.63
    
    0.63
    fjspx
    0.61
    IsMutable
    0.59
    setVerticalGroup
    0.58
     mapStateToProps
    0.57
    SharedDtor
    0.57
    RegressionTest
    0.57
     ***!
    0.56
    Activations Density 0.446%

    No Known Activations