© 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. 22-GEMMASCOPE-RES-16K
    11. 10684
    Prev
    Next
    INDEX
    Explanations

    instances of the word "under" in various contexts

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

    "under"

    np_acts-logits-general · gemini-2.0-flash

    under followed by words

    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
     Bioaccumulative
    -0.54
    omeness
    -0.54
    astify
    -0.53
     Pingback
    -0.52
    antMatchers
    -0.52
     digress
    -0.51
    databind
    -0.50
     Picchu
    -0.50
    BuilderFactory
    -0.49
    Mär
    -0.49
    POSITIVE LOGITS
    neath
    1.00
    lining
    0.78
    Билгалдахарш
    0.76
     dure
    0.74
    utilized
    0.73
     circumstances
    0.71
    lay
    0.66
    grunns
    0.66
     oath
    0.64
    utili
    0.64
    Activations Density 0.153%

    No Known Activations