© 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. 11465
    Prev
    Next
    INDEX
    Explanations

    sentences discussing personal growth and transformative experiences

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

    Follows a contrast conjunction

    np_acts-logits-general · gemini-2.0-flash

    but, and, then

    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
    zzleHttp
    -0.77
    setupUi
    -0.71
     Réponses
    -0.67
    GEBURTSDATUM
    -0.66
    Bronnen
    -0.63
     HasFactory
    -0.63
    MemoryWarning
    -0.61
    BeginContext
    -0.61
    Спасылкі
    -0.60
    TestBed
    -0.60
    POSITIVE LOGITS
     soon
    2.93
    Soon
    2.50
     Soon
    2.46
    soon
    2.46
     quickly
    2.38
    quickly
    2.10
     Quickly
    2.02
     SOON
    1.97
    Quickly
    1.95
     foon
    1.94
    Activations Density 0.506%

    No Known Activations