© 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. 11969
    Prev
    Next
    INDEX
    Explanations

    patterns in mathematical expressions or complex formulas with nested structures

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

    Arrays or matrices

    np_acts-logits-general · gemini-2.0-flash

    mathematical matrices and arrays

    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
    Erreferentziak
    -0.58
    Demografia
    -0.57
     CanadaChoose
    -0.53
    setCellValue
    -0.53
    RegistryLite
    -0.52
    thâu
    -0.50
    jspb
    -0.49
    وصلات
    -0.48
    ífer
    -0.48
     brz
    -0.48
    POSITIVE LOGITS
     ExecuteAsync
    0.65
    WriteTagHelper
    0.60
     MonoBehaviour
    0.60
    array
    0.56
    HtmlAttribute
    0.56
     vinted
    0.55
    UserScript
    0.54
    álen
    0.53
     handleMessage
    0.51
     FontWeight
    0.50
    Activations Density 0.041%

    No Known Activations