© 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. 7996
    Prev
    Next
    INDEX
    Explanations

    phrases that express skepticism or critical viewpoints

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

    Adverbs that modify adjectives or verbs

    np_acts-logits-general · gemini-2.0-flash

    often extreme qualifiers

    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
    ⎢
    -0.52
    󠁢
    -0.50
    taus
    -0.45
    χη
    -0.45
     Dressed
    -0.44
     alluminio
    -0.43
    XN
    -0.43
     tuong
    -0.42
    makin
    -0.41
    Становништво
    -0.41
    POSITIVE LOGITS
     downright
    1.36
     outright
    1.16
    RenderAtEndOf
    0.86
     carré
    0.84
     nakalista
    0.81
     jopa
    0.77
     almost
    0.76
     sogar
    0.72
    AddTagHelper
    0.71
    CppMethod
    0.71
    Activations Density 0.323%

    No Known Activations