© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 13088
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a journey or progress toward a destination

    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
    AndEndTag
    -0.85
    ValueStyle
    -0.75
     disambiguazione
    -0.72
     pinulongan
    -0.71
    WriteTagHelper
    -0.68
    TAINMENT
    -0.65
    tencent
    -0.64
     hjär
    -0.63
    WidgetItem
    -0.62
     onItemClick
    -0.62
    POSITIVE LOGITS
    sizeCache
    0.58
     camino
    0.57
     rumbo
    0.56
     toward
    0.54
     menuju
    0.51
    way
    0.50
     allerede
    0.49
    Toward
    0.48
     homeward
    0.48
     Hongrie
    0.47
    Activations Density 0.398%

    No Known Activations