© 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. 20-GEMMASCOPE-RES-16K
    11. 10605
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases associated with the idea of maintaining or tracking information

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

    "keep"

    np_acts-logits-general · gemini-2.0-flash

    keep + preposition/adverb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -1.13
    OGND
    -0.99
    ValueStyle
    -0.93
     Italijanski
    -0.81
     ujednoznacz
    -0.80
    homonymie
    -0.79
     Савезне
    -0.76
    writeFieldEnd
    -0.72
     Meksiku
    -0.72
    colgroup
    -0.71
    POSITIVE LOGITS
     track
    1.11
     keep
    0.91
     pace
    0.90
     Keep
    0.85
     keeps
    0.85
    keep
    0.82
    Keep
    0.82
     kept
    0.80
     abreast
    0.80
    Keeps
    0.78
    Activations Density 0.042%

    No Known Activations