© 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. 16-GEMMASCOPE-RES-16K
    11. 14027
    Prev
    Next
    INDEX
    Explanations

    terms related to support, encouragement, and fostering collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after "encourage" or "foster"

    np_acts-logits-general · gemini-2.0-flash

    encourage and foster

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Konsequ
    -0.53
    az
    -0.49
    claimers
    -0.47
    h
    -0.46
    готовление
    -0.46
    azin
    -0.45
    agara
    -0.44
    clientY
    -0.44
    asen
    -0.44
    ClientRect
    -0.43
    POSITIVE LOGITS
    
    0.97
    WriteTagHelper
    0.84
    ContentAsync
    0.83
    sizeCache
    0.79
    antaranya
    0.78
    tvguidetime
    0.77
     فريبيس
    0.76
    Bioaccumulative
    0.75
     growth
    0.75
     resourceCulture
    0.74
    Activations Density 0.240%

    No Known Activations