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. 2-GEMMASCOPE-RES-16K
    6. 12958
    Prev
    Next
    INDEX
    Explanations

    references to financial charges or costs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     feel
    -0.47
    jspb
    -0.45
     ***!
    -0.44
    WriteTagHelper
    -0.44
    ContentAsync
    -0.43
     perfection
    -0.43
     المقد
    -0.43
     emulate
    -0.42
     Hang
    -0.42
    VideoCapture
    -0.42
    POSITIVE LOGITS
     fees
    2.48
     Fees
    2.22
    Fees
    1.99
    fees
    1.91
     FEES
    1.77
     charges
    1.50
     Gebühren
    1.49
     costs
    1.37
     expenses
    1.34
     Charges
    1.34
    Activations Density 0.135%

    No Known Activations