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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 51889
    Prev
    Next
    INDEX
    Explanations

    instances of teaching, support, and guidance in educational contexts

    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
     Мексичка
    -0.63
     surla
    -0.61
    󠁣
    -0.58
     AssemblyVersion
    -0.56
    setVerticalGroup
    -0.56
     esternos
    -0.55
    ngdoc
    -0.55
    webElementXpaths
    -0.54
    цездатний
    -0.54
    󠁴
    -0.54
    POSITIVE LOGITS
     encourage
    0.45
     encouragement
    0.42
     encouraged
    0.41
    encouragement
    0.39
     encourag
    0.38
     stav
    0.35
     encourages
    0.34
     encouraging
    0.34
     supervision
    0.33
     chod
    0.32
    Activations Density 0.037%

    No Known Activations