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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 92309
    Prev
    Next
    INDEX
    Explanations

    technical components and specifications related to devices and machinery

    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
    athies
    -0.44
    例文
    -0.44
    mering
    -0.44
     createState
    -0.42
     zdan
    -0.42
    phard
    -0.41
    letons
    -0.41
     Targeted
    -0.41
     terrorists
    -0.40
     feder
    -0.40
    POSITIVE LOGITS
     Italijanski
    0.61
    HasIndex
    0.48
    Tikang
    0.48
    writeFieldEnd
    0.48
    InjectAttribute
    0.46
     magnético
    0.46
     שוליים
    0.46
     EconPapers
    0.45
     Wikiseite
    0.45
    󠁴
    0.44
    Activations Density 0.002%

    No Known Activations