© 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. 12016
    Prev
    Next
    INDEX
    Explanations

    references to scientific data and documentation

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

    Accessed dates from URLs

    np_acts-logits-general · gemini-2.0-flash

    (accessed date)

    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
    PhysRevD
    -0.91
    تقاوى
    -0.81
    WithIOException
    -0.78
     defaultstate
    -0.74
    AutoField
    -0.72
    Portail
    -0.71
    InstrumentedTest
    -0.70
    basicConfig
    -0.70
    RegressionTest
    -0.69
    nocache
    -0.66
    POSITIVE LOGITS
     للاسماء
    0.44
    ciful
    0.41
     indir
    0.40
     navegando
    0.40
    ulter
    0.40
     getty
    0.39
    findpost
    0.39
    ebook
    0.39
     Betrieb
    0.38
     typelib
    0.38
    Activations Density 0.047%

    No Known Activations