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. 90043
    Prev
    Next
    INDEX
    Explanations

    verbs and conjunctions that indicate comparisons and changes in state or condition

    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
    Personendaten
    -0.55
    énario
    -0.55
     otomatig
    -0.50
    󠁣
    -0.40
     generational
    -0.40
    ✭✭
    -0.39
     pulito
    -0.39
     Shawn
    -0.38
    FACTS
    -0.37
     Sag
    -0.37
    POSITIVE LOGITS
    abestanden
    0.62
    ngdoc
    0.55
    IBOutlet
    0.54
     ExecuteAsync
    0.53
    ItemLayout
    0.52
     '{@
    0.51
    IUrlHelper
    0.49
    ChildScrollView
    0.48
    tagHelperRunner
    0.47
     jsPsych
    0.46
    Activations Density 0.212%

    No Known Activations