© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 3886
    Prev
    Next
    INDEX
    Explanations

    terms related to intelligence and academic language

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     disponibilités
    -0.52
    tonode
    -0.50
    脚注の使い方
    -0.44
     StringTokenizer
    -0.43
     Stakeholders
    -0.42
    landais
    -0.41
    Referències
    -0.40
    водитель
    -0.40
    بوابة
    -0.39
     ApiResponse
    -0.39
    POSITIVE LOGITS
    TypedDataSet
    0.55
    Formatter
    0.52
     jaz
    0.50
    Sent
    0.49
     blu
    0.48
     intelligently
    0.45
     clever
    0.44
    Ӕ
    0.44
    agisse
    0.43
    dell
    0.43
    Activations Density 1.737%

    No Known Activations