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-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15690
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to "trans" (across, through) in various contexts, especially in scientific and technical literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    starting with "trans" or "Trans"

    np_acts-logits-general · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.53
     MainAxisSize
    -0.43
     iNdEx
    -0.43
    kaar
    -0.40
     rzecz
    -0.38
     ErrorMessage
    -0.38
    excuse
    -0.37
    principalColumn
    -0.36
    inafter
    -0.36
    Còn
    -0.36
    POSITIVE LOGITS
     trans
    1.05
     Trans
    1.04
    Trans
    0.89
    trans
    0.86
     TRANS
    0.80
    TRANS
    0.75
     TRAN
    0.66
     Tans
    0.59
     Transylvania
    0.58
    TRAN
    0.57
    Activations Density 0.166%

    No Known Activations