© 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. 12006
    Prev
    Next
    INDEX
    Explanations

    the conjunction "and" in various contexts

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

    Immediately after the word "and"

    np_acts-logits-general · gemini-2.0-flash

    and followed by related words

    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
    zumaki
    -0.52
    lipe
    -0.49
    pixabay
    -0.48
    webElementXpaths
    -0.46
    меч
    -0.46
    kesha
    -0.45
     kura
    -0.45
     sem
    -0.45
     spre
    -0.44
     Milan
    -0.44
    POSITIVE LOGITS
     CreateTagHelper
    0.91
    RegressionTest
    0.85
    __':
    0.77
    saraba
    0.76
    RenderAtEndOf
    0.75
     Мексичка
    0.70
    GEBURTSDATUM
    0.69
     Theſe
    0.69
    UserScript
    0.69
    endphp
    0.68
    Activations Density 0.153%

    No Known Activations