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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 57334
    Prev
    Next
    INDEX
    Explanations

    terms related to nozzle and jetting processes in fluid systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.81
    mybatisplus
    -0.79
    adaptiveStyles
    -0.64
    TemporalType
    -0.64
     Signalez
    -0.60
    abetes
    -0.58
    Архівовано
    -0.56
    orianCalendar
    -0.56
     समीक्षाओं
    -0.56
    BASEPATH
    -0.55
    POSITIVE LOGITS
     nozzle
    0.86
     Nozzle
    0.82
     nozzles
    0.66
    zzle
    0.46
     outlet
    0.43
     drenaje
    0.42
     tuyau
    0.42
     channel
    0.41
     Motto
    0.41
    嘴
    0.41
    Activations Density 0.026%

    No Known Activations