© 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. 22-GEMMASCOPE-RES-16K
    11. 6789
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence or absence of something in relation to doing or achieving something

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

    followed by "to do" or "do"

    np_acts-logits-general · gemini-2.0-flash

    to do with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     soort
    -0.56
     مُعرِّف
    -0.55
    طيع
    -0.52
    ultati
    -0.52
     Monfieur
    -0.52
    variates
    -0.51
     poffible
    -0.51
    arsis
    -0.51
     ftate
    -0.51
     uſed
    -0.51
    POSITIVE LOGITS
     do
    1.49
    do
    1.22
     Do
    1.06
    Do
    1.05
     DO
    1.02
     propOrder
    0.88
     does
    0.84
    DO
    0.83
     doe
    0.69
     anything
    0.67
    Activations Density 0.104%

    No Known Activations