© 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. 3759
    Prev
    Next
    INDEX
    Explanations

    verbs indicating movement or transition

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

    "goes" followed by a preposition

    np_acts-logits-general · gemini-2.0-flash

    verb "go" followed by common prepositions

    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
    NOPQRST
    -0.52
    ailleurs
    -0.47
    っきり
    -0.47
    stretchr
    -0.47
    isSet
    -0.46
    alba
    -0.46
     referenties
    -0.45
    itatis
    -0.45
    ObjectMapper
    -0.44
     kuda
    -0.44
    POSITIVE LOGITS
     disambiguazione
    0.84
    Goes
    0.80
     GOES
    0.76
     Goes
    0.75
     goes
    0.70
     autorytatywna
    0.70
    Билгалдахарш
    0.70
    twimg
    0.66
    goes
    0.64
     typelib
    0.60
    Activations Density 0.135%

    No Known Activations