© 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. 2012
    Prev
    Next
    INDEX
    Explanations

    adverbs that describe methods or qualities of actions, often indicating how something is done

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

    ending in "-ly"

    np_acts-logits-general · gemini-2.0-flash

    adverbs followed by descriptive words

    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
    есть
    -0.58
    timate
    -0.58
    ultimate
    -0.58
     ultimate
    -0.56
    al
    -0.55
    B
    -0.54
    poc
    -0.53
    an
    -0.53
    k
    -0.53
    b
    -0.52
    POSITIVE LOGITS
    AddTagHelper
    0.83
    #
    0.81
    ']")
    0.76
     بيها
    0.75
     تضيفلها
    0.74
    ''');
    0.73
    "]),
    0.70
    outube
    0.70
     ligiloj
    0.68
    liggende
    0.68
    Activations Density 0.596%

    No Known Activations