© 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. 3453
    Prev
    Next
    INDEX
    Explanations

    code elements related to functions and operators in programming

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

    Code: push_back, insert, resize, data, begin, end, center

    np_acts-logits-general · gemini-2.0-flash

    programming operators

    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
    posites
    -0.58
    بوابة
    -0.58
     fris
    -0.55
     feeling
    -0.52
     pageable
    -0.50
     وتسجيلات
    -0.48
    Feeling
    -0.48
    اه
    -0.48
    Chham
    -0.47
    feeling
    -0.46
    POSITIVE LOGITS
    operator
    1.04
     operator
    0.89
     OPERATOR
    0.70
     Operator
    0.63
     operators
    0.60
     ((*
    0.58
    (*
    0.57
     Operators
    0.56
     operador
    0.55
    ",&
    0.54
    Activations Density 0.110%

    No Known Activations