© 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. 5216
    Prev
    Next
    INDEX
    Explanations

    references to cooperation and shared actions

    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
     JpaRepository
    -0.60
    complexContent
    -0.58
     handleMessage
    -0.47
     biografias
    -0.47
    ')";
    -0.46
    __*/
    -0.46
    μένος
    -0.45
     connectors
    -0.44
     erhielt
    -0.44
     thyself
    -0.44
    POSITIVE LOGITS
     gemeinsame
    0.75
     together
    0.73
     gemeinsamen
    0.69
     collectively
    0.69
     shared
    0.69
     juntos
    0.66
     Together
    0.65
    Together
    0.65
     一起
    0.64
     jointly
    0.64
    Activations Density 0.376%

    No Known Activations