© 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. 7799
    Prev
    Next
    INDEX
    Explanations

    Python function and variable definitions, along with control flow structures

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

    Code, functions, or programming-related names

    np_acts-logits-general · gemini-2.0-flash

    programming keywords followed by punctuation

    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
    ])){
    -0.50
     Py
    -0.48
    endregion
    -0.45
    Py
    -0.43
    windowFixed
    -0.43
    pyp
    -0.41
    ))){
    -0.41
     off
    -0.40
    radan
    -0.40
    кій
    -0.40
    POSITIVE LOGITS
    tvguidetime
    0.73
     Wicidata
    0.73
     kasarigan
    0.70
     Drapeau
    0.70
    onsored
    0.67
     initComponents
    0.65
    igshid
    0.64
    ähig
    0.64
    mappedBy
    0.63
    SqlClient
    0.63
    Activations Density 0.086%

    No Known Activations