© 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-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 31893
    Prev
    Next
    INDEX
    Explanations

    references to client relationships and marketing services

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    client service and business development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    likat
    -0.53
    ="@+
    -0.50
    Volunteers
    -0.47
     MonoBehaviour
    -0.46
    Hast
    -0.46
    GOTREF
    -0.45
     cruce
    -0.45
    тение
    -0.44
     Volunteers
    -0.44
     menstru
    -0.44
    POSITIVE LOGITS
     client
    1.74
     clients
    1.65
     Clients
    1.52
     Client
    1.52
    Clients
    1.36
    Client
    1.35
    client
    1.35
     CLIENT
    1.27
     clientes
    1.27
    CLIENT
    1.27
    Activations Density 0.212%

    No Known Activations