© 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. 4-GEMMASCOPE-RES-16K
    11. 10530
    Prev
    Next
    INDEX
    Explanations

    references to collective or joint actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sidemargin
    -0.50
     AssemblyTitle
    -0.50
    enda
    -0.45
     no
    -0.44
     not
    -0.41
    FlatStyle
    -0.40
     a
    -0.40
    udge
    -0.39
    ържа
    -0.38
    bujete
    -0.38
    POSITIVE LOGITS
    Together
    1.68
     together
    1.64
     Together
    1.63
     TOGETHER
    1.61
    together
    1.59
     jointly
    1.36
     juntos
    1.35
     gemeinsam
    1.26
     razem
    1.25
    Zusammen
    1.23
    Activations Density 0.319%

    No Known Activations