Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 10451
    Prev
    Next
    INDEX
    Explanations

    references to regulatory actions and market investigations

    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
    cshtml
    -0.43
    InjectAttribute
    -0.41
    下载附件
    -0.36
    anyway
    -0.35
     Anyway
    -0.35
    Anyway
    -0.34
     gainera
    -0.34
     Majesté
    -0.33
     Probably
    -0.33
    saraba
    -0.33
    POSITIVE LOGITS
     reports
    1.46
     concerns
    1.41
     rumors
    1.40
     allegations
    1.38
     accusations
    1.34
     criticism
    1.34
     rumours
    1.34
     criticisms
    1.33
     complaints
    1.30
     calls
    1.27
    Activations Density 0.949%

    No Known Activations