© 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. 16-GEMMASCOPE-RES-16K
    11. 2636
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contrast or comparison

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

    "too"

    np_acts-logits-general · gemini-2.0-flash

    adding emphasis or inclusion

    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
    stdc
    -0.81
    Personensuche
    -0.69
     Ceinture
    -0.66
    InitVars
    -0.64
    ViewInit
    -0.63
     betweenstory
    -0.63
     ModelRenderer
    -0.62
    TypedDataSet
    -0.62
     JADX
    -0.61
     newBuilder
    -0.61
    POSITIVE LOGITS
     esterni
    0.80
    たまた
    0.79
     kasarigan
    0.74
     zwar
    0.66
    fortawesome
    0.65
     שוליים
    0.63
     חיצוניים
    0.60
    즉
    0.58
    </i>
    0.57
    amie
    0.56
    Activations Density 1.417%

    No Known Activations