© 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. 11-GEMMASCOPE-RES-16K
    11. 4372
    Prev
    Next
    INDEX
    Explanations

    numerical values and their relationships in data configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    invokeLater
    -0.51
    дав
    -0.50
    </em>
    -0.47
    ]")]
    -0.45
    tip
    -0.45
     Gottlieb
    -0.45
     to
    -0.44
    -
    -0.43
     la
    -0.43
    ’
    -0.42
    POSITIVE LOGITS
     itſelf
    0.93
     myſelf
    0.87
     Monfieur
    0.85
     Chrif
    0.82
     Efq
    0.81
     poffe
    0.80
     houſe
    0.79
     themſelves
    0.79
     Theſe
    0.78
     Jefus
    0.76
    Activations Density 0.699%

    No Known Activations