© 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. 115627
    Prev
    Next
    INDEX
    Explanations

    terms related to programming and technical specifications

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

    code and multilingual text

    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
     ulang
    -0.41
     sombra
    -0.38
     magnética
    -0.37
     interesan
    -0.36
     cafetería
    -0.35
     INFORMACIÓN
    -0.35
     fournis
    -0.35
     Kommentare
    -0.35
    cripciones
    -0.34
     Infrastruktur
    -0.34
    POSITIVE LOGITS
     мәкал
    1.77
    tagHelperRunner
    1.63
    httphttps
    1.59
     незавершена
    1.55
     pinulongan
    1.53
     ویکی‌پدی
    1.51
    تقاوى
    1.49
     kaarangay
    1.44
    GEBURTSDATUM
    1.36
    hoeddwyd
    1.35
    Activations Density 0.002%

    No Known Activations