© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 11419
    Prev
    Next
    INDEX
    Explanations

    references to services, particularly those involving pricing and economic value

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.43
    usermodel
    -0.37
    )_/¯
    -0.36
    IntoConstraints
    -0.36
     externi
    -0.34
    ❹
    -0.33
    extAlignment
    -0.33
     mergeFrom
    -0.33
    ">//
    -0.33
    sonaro
    -0.33
    POSITIVE LOGITS
     services
    3.34
    services
    2.80
     Services
    2.69
     SERVICES
    2.59
    Services
    2.56
     service
    2.48
     servicios
    2.47
     serviços
    2.38
    SERVICES
    2.25
     servizi
    2.22
    Activations Density 0.476%

    No Known Activations