© 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. 20-GEMMASCOPE-RES-16K
    11. 3807
    Prev
    Next
    INDEX
    Explanations

    references to specific settings or situations involving food or social gatherings

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

    Code snippets or technical jargon

    np_acts-logits-general · gemini-2.0-flash

    recruitment, security, them

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     it
    -0.74
     etc
    -0.57
     itp
    -0.56
     itd
    -0.55
    >(),
    -0.54
     оно
    -0.53
     strpos
    -0.49
    "],
    -0.48
    extAlignment
    -0.47
     это
    -0.47
    POSITIVE LOGITS
    findpost
    0.82
     ligiloj
    0.77
     виправивши
    0.73
    IUrlHelper
    0.69
     beginnetje
    0.68
     ModelRenderer
    0.65
    rungsseite
    0.65
     estekak
    0.63
     AssemblyCulture
    0.63
     ***!
    0.63
    Activations Density 0.413%

    No Known Activations