© 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. 18-GEMMASCOPE-RES-16K
    11. 11344
    Prev
    Next
    INDEX
    Explanations

    instances of the word "at" and its variations, indicating locations or times

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

    "At" followed by a temporal word ("first," "that," "this," "all")

    np_acts-logits-general · gemini-2.0-flash

    at first, at some, at least, at this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jspb
    -0.66
     proposons
    -0.62
    impianto
    -0.61
    jspb
    -0.58
     وتسجيلات
    -0.57
    GEBURTSDATUM
    -0.57
    ورية
    -0.56
    zijde
    -0.56
    bibfield
    -0.56
    ximately
    -0.56
    POSITIVE LOGITS
    XmlAccessorType
    0.49
     really
    0.47
    gento
    0.43
    Referências
    0.43
    ::~
    0.41
    KURZBESCHREIBUNG
    0.41
     least
    0.40
     fura
    0.39
     Vikipedi
    0.39
    ″]
    0.39
    Activations Density 0.122%

    No Known Activations