© 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. 1256
    Prev
    Next
    INDEX
    Explanations

    elements related to data structures and error handling in programming

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

    Code snippets with operators

    np_acts-logits-general · gemini-2.0-flash

    assignment and error handling

    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
    ThroughAttribute
    -0.78
    SequentialGroup
    -0.75
    principalColumn
    -0.71
    UserScript
    -0.70
     فريبيس
    -0.67
     EconPapers
    -0.66
    InitVars
    -0.66
     通販
    -0.63
    NameInMap
    -0.62
    AddTagHelper
    -0.61
    POSITIVE LOGITS
     :=
    0.78
     <-
    0.61
    :=
    0.54
    select
    0.52
     NgModule
    0.52
    <-
    0.47
    CPtr
    0.43
     select
    0.43
    makeConstraints
    0.40
    críbete
    0.39
    Activations Density 0.132%

    No Known Activations