© 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. 7-GEMMASCOPE-RES-16K
    11. 12511
    Prev
    Next
    INDEX
    Explanations

    the word "selected" and its variations, indicating an emphasis on selection processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EObject
    -0.93
     errMsg
    -0.90
    rativa
    -0.87
     maxn
    -0.84
     PIE
    -0.79
     propOrder
    -0.76
     FH
    -0.74
    etCode
    -0.73
     cauza
    -0.72
    bcrypt
    -0.71
    POSITIVE LOGITS
     Sele
    1.36
     selections
    1.29
    Selection
    1.27
     Selection
    1.26
     selection
    1.24
     Selections
    1.21
    Sele
    1.20
     sele
    1.19
     Selected
    1.15
     selected
    1.14
    Activations Density 0.056%

    No Known Activations