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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 15697
    Prev
    Next
    INDEX
    Explanations

    HTML select elements and their associated attributes and options

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     يتيمه
    -0.81
    OCCURRED
    -0.72
     Photocase
    -0.69
    脚注の使い方
    -0.65
    BeginContext
    -0.64
    matchCondition
    -0.64
    WebVitals
    -0.64
    parsedMessage
    -0.62
    enderror
    -0.62
    tagHelperRunner
    -0.60
    POSITIVE LOGITS
     JComboBox
    0.79
    JComboBox
    0.79
     choix
    0.60
    select
    0.60
    ComboBox
    0.60
     choices
    0.59
     sélectionner
    0.57
    bobox
    0.57
     select
    0.57
     selects
    0.56
    Activations Density 0.121%

    No Known Activations