© 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
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 13630
    Prev
    Next
    INDEX
    Explanations

    instances of the word "and" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    呼ば
    -0.84
    一緒に
    -0.77
    其他
    -0.71
    言い
    -0.70
    考え
    -0.66
    共に
    -0.60
    思い
    -0.59
    考えて
    -0.57
    その
    -0.55
    同じ
    -0.55
    POSITIVE LOGITS
     zwar
    0.68
    ersen
    0.52
    amento
    0.49
     puis
    0.46
    romeda
    0.46
    Beyond
    0.45
    脚注の使い方
    0.44
    点此举报
    0.44
     مرئيه
    0.44
    amenti
    0.42
    Activations Density 0.307%

    No Known Activations