© 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. 16-GEMMASCOPE-RES-16K
    11. 9567
    Prev
    Next
    INDEX
    Explanations

    concepts related to business ethics and social responsibility

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    UrlResolution
    -0.74
     المعيارى
    -0.69
    uxxxx
    -0.62
     فريبيس
    -0.61
     AssemblyCompany
    -0.59
    BeginContext
    -0.59
     SwitchCompat
    -0.55
    Pops
    -0.54
    oxide
    -0.54
    ximately
    -0.54
    POSITIVE LOGITS
     suivante
    0.36
     estudian
    0.35
    }])
    0.32
    RuleContext
    0.32
    EndContext
    0.31
    ,
    0.30
     Offisielt
    0.30
     quiser
    0.30
     ámbito
    0.29
    utilisons
    0.29
    Activations Density 0.135%

    No Known Activations