Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 14407
    Prev
    Next
    INDEX
    Explanations

    the word "most" along with phrases indicating majority or consensus

    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
    aryen
    -0.56
    JNIEnv
    -0.54
    Filed
    -0.50
     Schild
    -0.50
    setField
    -0.49
     Martel
    -0.48
    PathVariable
    -0.48
     fieldwork
    -0.47
    äischen
    -0.47
     Paren
    -0.47
    POSITIVE LOGITS
     MOST
    0.86
    most
    0.83
    Most
    0.82
     Most
    0.81
     most
    0.80
     maioria
    0.77
    MOST
    0.76
     plupart
    0.75
     meisten
    0.75
     majority
    0.70
    Activations Density 0.116%

    No Known Activations