© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104664
    Prev
    Next
    INDEX
    Explanations

    structured data formats or elements commonly used in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     çıktı
    -0.35
     kaynağından
    -0.33
     
    -0.32
    
    -0.31
     satisfied
    -0.30
     small
    -0.30
     kaybet
    -0.30
     дописавши
    -0.28
     a
    -0.27
    y
    -0.27
    POSITIVE LOGITS
     queſta
    0.86
    iſen
    0.83
     ſind
    0.82
     ویکی‌پدی
    0.81
    XmlAccessType
    0.79
    нгред
    0.74
    <unused79>
    0.73
    ſehen
    0.73
    [@BOS@]
    0.73
    <unused3>
    0.73
    Activations Density 0.022%

    No Known Activations