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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 120357
    Prev
    Next
    INDEX
    Explanations

    terms related to technical processes and measurements in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     modeled
    -0.26
    到位
    -0.24
    mapStateToProps
    -0.23
     عص
    -0.23
    j
    -0.22
    判
    -0.22
     сим
    -0.21
    ^{
    -0.20
     вход
    -0.20
    URLs
    -0.20
    POSITIVE LOGITS
    webElementXpaths
    0.97
    AndEndTag
    0.91
     <<<<<<<<<<<<<<
    0.87
    webElementGuid
    0.82
    OGND
    0.81
     estekak
    0.81
     فريبيس
    0.80
     صوتيه
    0.77
    BeginContext
    0.77
    :✨
    0.77
    Activations Density 0.054%

    No Known Activations