© 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. 10-GEMMASCOPE-RES-16K
    6. 6254
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the word "most" to convey a sense of majority or prevalence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Martel
    -0.59
    programme
    -0.54
     Symbol
    -0.54
     cheque
    -0.53
     Ename
    -0.52
    cheque
    -0.52
     papier
    -0.51
     card
    -0.51
     CURIAM
    -0.50
     Coder
    -0.50
    POSITIVE LOGITS
     most
    1.32
    Most
    1.25
    most
    1.25
     Most
    1.22
     MOST
    1.20
    MOST
    1.06
     moſt
    0.94
     meisten
    0.92
     moft
    0.91
     plupart
    0.91
    Activations Density 0.114%

    No Known Activations