© 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. 8202
    Prev
    Next
    INDEX
    Explanations

    words associated with twisting or contorting actions

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

    starting with "Tw" or containing "tw"

    np_acts-logits-general · gemini-2.0-flash

    "Tw" and related action verbs

    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
     RemoteException
    -0.58
    requireNonNull
    -0.56
     Selecciona
    -0.54
    ección
    -0.54
     Kearns
    -0.54
    AnchorTagHelper
    -0.53
     segn
    -0.52
     SOT
    -0.52
    inheritdoc
    -0.52
    MHC
    -0.52
    POSITIVE LOGITS
     Tw
    1.08
     tw
    0.96
    Tw
    0.91
    tw
    0.87
     TW
    0.84
     Twins
    0.81
    Twins
    0.78
     twister
    0.77
     Twe
    0.75
     Twit
    0.73
    Activations Density 0.167%

    No Known Activations