© 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. 8040
    Prev
    Next
    INDEX
    Explanations

    phrases expressing positivity or enthusiasm

    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
    AddTagHelper
    -0.64
    ItemBackground
    -0.63
     canst
    -0.59
    principalTable
    -0.59
     وتسجيلات
    -0.54
     informée
    -0.52
     ffilmiau
    -0.52
    writeFieldEnd
    -0.50
    それも
    -0.49
     DevComponents
    -0.49
    POSITIVE LOGITS
    Excellent
    0.84
    Great
    0.83
    Amazing
    0.82
     Excellent
    0.81
    Wonderful
    0.81
     Wonderful
    0.80
    Excelente
    0.79
     Great
    0.79
    Awesome
    0.78
    Fantastic
    0.77
    Activations Density 0.074%

    No Known Activations