© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 15804
    Prev
    Next
    INDEX
    Explanations

    financial terminology related to stocks and investments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.60
     atve
    -0.48
     Infórmanos
    -0.40
    vitational
    -0.38
     warm
    -0.37
     partielle
    -0.36
    mige
    -0.36
    omock
    -0.36
    冷
    -0.35
     zorro
    -0.35
    POSITIVE LOGITS
     JpaRepository
    0.50
    はじめに
    0.49
    
    0.47
     differentiated
    0.47
     ModelExpression
    0.43
    urahan
    0.43
    comuna
    0.43
    offsetof
    0.42
     dividend
    0.42
    Executives
    0.41
    Activations Density 0.318%

    No Known Activations