© 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 - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 8022
    Prev
    Next
    INDEX
    Explanations

    key geopolitical entities and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.56
    glide
    -0.53
    存于互联网档案馆
    -0.49
    MLLoader
    -0.47
    TagMode
    -0.46
     للمعارف
    -0.45
    fxml
    -0.44
    kháu
    -0.44
    endphp
    -0.44
    DockStyle
    -0.43
    POSITIVE LOGITS
     Saudi
    0.91
    Saudi
    0.79
     السعود
    0.59
     Arabia
    0.56
     Arabian
    0.54
     Riyadh
    0.52
    yadh
    0.52
     Saud
    0.52
     سعود
    0.49
     gyhoeddwyd
    0.47
    Activations Density 0.317%

    No Known Activations