© 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. 11958
    Prev
    Next
    INDEX
    Explanations

    references to medical screening and health-related topics, particularly pertaining to mammograms and related terms

    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
    -0.53
    IndentedString
    -0.53
    ThroughAttribute
    -0.52
     unknownFields
    -0.52
     незавершена
    -0.48
    bilirsiniz
    -0.43
    errHandler
    -0.43
     autorytatywna
    -0.42
    jší
    -0.41
    вості
    -0.41
    POSITIVE LOGITS
     mam
    0.63
     Mam
    0.63
    Mam
    0.60
     Mom
    0.58
     mum
    0.58
     mamá
    0.58
    Mom
    0.55
     mom
    0.55
     Mum
    0.54
     ModelExpression
    0.54
    Activations Density 0.170%

    No Known Activations