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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 8611
    Prev
    Next
    INDEX
    Explanations

    occurrences of leadership and collaborative team dynamics in professional contexts

    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
     snippetHide
    -0.50
     Wirksamkeit
    -0.45
     empleos
    -0.41
    原始内容存档
    -0.41
    wezen
    -0.41
     automatiques
    -0.41
     succès
    -0.40
     officielle
    -0.40
    原始内容存档于
    -0.39
     meurt
    -0.39
    POSITIVE LOGITS
     Subject
    0.83
     subject
    0.80
     senior
    0.71
    Subject
    0.69
     VP
    0.69
     analysts
    0.68
    subject
    0.66
     internal
    0.66
     Senior
    0.65
     analyst
    0.64
    Activations Density 0.311%

    No Known Activations