© 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. 10-GEMMASCOPE-RES-16K
    11. 8725
    Prev
    Next
    INDEX
    Explanations

    references to organized events and collaborations

    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
     AssemblyCulture
    -0.79
    ThroughAttribute
    -0.64
    Clik
    -0.62
    AndroidJUnit
    -0.57
     MotionEvent
    -0.56
    runApp
    -0.54
     StatelessWidget
    -0.53
    userdetails
    -0.53
    +#+#
    -0.53
    DidLoad
    -0.53
    POSITIVE LOGITS
     sponsored
    0.77
     patrocin
    0.65
     auspices
    0.64
     ausp
    0.63
     sponsors
    0.61
    sponsored
    0.60
     jointly
    0.59
    λία
    0.58
     cordially
    0.58
    主催
    0.56
    Activations Density 0.169%

    No Known Activations