© 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. 11-GEMMASCOPE-RES-16K
    11. 4811
    Prev
    Next
    INDEX
    Explanations

    references to academic roles and institutions related to social and cultural studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.47
    ✢
    -0.45
    ❋
    -0.45
     Taktlose
    -0.43
     kaarangay
    -0.42
    Rhestr
    -0.42
     beteken
    -0.41
    脚注の使い方
    -0.40
    ViewById
    -0.39
    jspb
    -0.37
    POSITIVE LOGITS
     professors
    0.69
     professor
    0.67
     Professors
    0.64
     Professor
    0.60
    Professor
    0.60
     faculty
    0.57
    professor
    0.56
    教授
    0.55
     profesora
    0.52
     PROFESSOR
    0.50
    Activations Density 0.700%

    No Known Activations