© 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. 15329
    Prev
    Next
    INDEX
    Explanations

    various programming constructs and syntax elements related to data handling in code

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

    Code snippets related to autorest

    np_acts-logits-general · gemini-2.0-flash

    autorest and category listings

    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
    leneck
    -0.45
     pí
    -0.44
     assoluto
    -0.44
     lockers
    -0.41
     objec
    -0.40
    Wire
    -0.39
     الحره
    -0.39
     Annu
    -0.39
     Klicken
    -0.38
    OBJECT
    -0.38
    POSITIVE LOGITS
    AndroidJUnit
    0.80
    RegressionTest
    0.73
     мәкал
    0.71
    MENAFN
    0.70
    )':
    0.67
    aarrggbb
    0.67
    =$?
    0.65
    >",
    0.64
    hdashline
    0.64
     transférez
    0.63
    Activations Density 0.018%

    No Known Activations