© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 8442
    Prev
    Next
    INDEX
    Explanations

    variations of the word "such" in different contexts

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

    "Such" followed by "a" or "an"

    np_acts-logits-general · gemini-2.0-flash

    such a or an

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.75
     alguna
    -0.68
     alguno
    -0.65
     some
    -0.62
     algunas
    -0.61
     algún
    -0.57
     algunos
    -0.57
     algum
    -0.55
     alguma
    -0.54
    AutoField
    -0.54
    POSITIVE LOGITS
     thing
    0.89
     рода
    0.88
     собі
    0.70
     lumin
    0.69
     drastic
    0.69
    thing
    0.68
     lofty
    0.67
     THING
    0.66
     blatant
    0.65
    maschinen
    0.64
    Activations Density 0.111%

    No Known Activations