© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 75838
    Prev
    Next
    INDEX
    Explanations

    assignments and operations typically seen in programming or script syntax

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

    fill, middle, width, +=

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     мәкал
    -0.65
    脚注の使い方
    -0.65
    ➟
    -0.62
     beſch
    -0.60
     ſehr
    -0.60
     autorytatywna
    -0.59
     ſelb
    -0.58
    <unused71>
    -0.58
    [@BOS@]
    -0.57
    <unused11>
    -0.57
    POSITIVE LOGITS
     enamorado
    0.35
    GeneratedMessage
    0.30
     respectivamente
    0.29
     asesinado
    0.28
     Bélgica
    0.28
     unknownFields
    0.28
     suavemente
    0.28
    writeFieldEnd
    0.28
     forcé
    0.27
     AssemblyCompany
    0.27
    Activations Density 0.013%

    No Known Activations