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. 29547
    Prev
    Next
    INDEX
    Explanations

    numerical values and their relationships within specific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numbers and limits

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    styleType
    -0.43
    AndPassword
    -0.37
     operas
    -0.36
    rxjs
    -0.34
     الأق
    -0.32
    IANGLES
    -0.32
    Edm
    -0.31
     Technic
    -0.31
     Ceremon
    -0.30
    setQuery
    -0.30
    POSITIVE LOGITS
    AsUp
    0.58
    Personensuche
    0.54
     ExecuteAsync
    0.51
     getMax
    0.51
     betweenstory
    0.51
    bouncycastle
    0.50
     disambiguazione
    0.50
    Spoljašnje
    0.48
     maksimal
    0.47
     BaseEntity
    0.47
    Activations Density 0.077%

    No Known Activations