© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8101
    Prev
    Next
    INDEX
    Explanations

    syntax elements commonly used in programming

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

    "new" or code related to "new"

    np_acts-logits-general · gemini-2.0-flash

    creating new code structures

    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
    gridColumn
    -0.53
    モト
    -0.51
    unton
    -0.49
    akos
    -0.47
     requestId
    -0.46
     qo
    -0.45
    ScopeManager
    -0.45
     hindurch
    -0.43
     hết
    -0.42
     Jacobs
    -0.42
    POSITIVE LOGITS
     new
    1.97
    new
    1.89
    New
    1.49
    新
    1.47
     NEW
    1.47
     New
    1.46
     neue
    1.43
     nieuwe
    1.39
     nuevas
    1.36
     nuovi
    1.36
    Activations Density 0.053%

    No Known Activations