© 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. 1-GEMMASCOPE-RES-16K
    11. 16012
    Prev
    Next
    INDEX
    Explanations

    references to musical groups or collaborations involving multiple members

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexContent
    -0.62
    enschappelijke
    -0.53
    揆
    -0.52
    signable
    -0.51
     many
    -0.51
     different
    -0.51
    sur
    -0.50
     Trabajo
    -0.49
     adipis
    -0.49
    abetes
    -0.49
    POSITIVE LOGITS
     duo
    3.35
     trio
    2.79
     Duo
    2.55
    Duo
    2.32
    duo
    2.24
     duos
    2.18
     Trio
    2.15
     quartet
    2.02
    Trio
    1.94
    trio
    1.74
    Activations Density 0.112%

    No Known Activations