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. 21-GEMMASCOPE-RES-16K
    6. 11953
    Prev
    Next
    INDEX
    Explanations

    references to financial investments and investing activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     parachoque
    -0.56
     Handler
    -0.55
     manners
    -0.54
    manner
    -0.54
     handlers
    -0.51
     Manner
    -0.50
     handler
    -0.50
    isNotBlank
    -0.50
     Barker
    -0.50
     Rahman
    -0.50
    POSITIVE LOGITS
     investment
    1.12
     INVESTMENT
    1.02
     Investment
    1.01
    Investment
    1.00
     invest
    0.98
     inversión
    0.94
    investment
    0.94
     investments
    0.93
     INVEST
    0.93
     invests
    0.90
    Activations Density 0.101%

    No Known Activations