© 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. 21-GEMMASCOPE-RES-16K
    11. 10337
    Prev
    Next
    INDEX
    Explanations

    phrases that convey a sense of helping or contributing towards positive outcomes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     AssemblyCulture
    -0.67
     ProtoMessage
    -0.63
     AssemblyCompany
    -0.62
    findpost
    -0.54
    AutoScaleMode
    -0.53
    gogo
    -0.53
    CppMethod
    -0.52
    下载附件
    -0.50
    ьажоргаш
    -0.49
    ArgsConstructor
    -0.49
    POSITIVE LOGITS
     achieving
    0.56
     attaining
    0.50
     improve
    0.49
     ensure
    0.48
     achieve
    0.47
    improve
    0.46
     sağlay
    0.46
    确保
    0.45
    Ensure
    0.44
     Sicherung
    0.44
    Activations Density 0.408%

    No Known Activations