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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 907
    Prev
    Next
    INDEX
    Explanations

    phrases related to health information access and control rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gas
    -0.57
     gas
    -0.56
     haver
    -0.48
     ha
    -0.48
    gis
    -0.47
     isComment
    -0.47
     hem
    -0.45
    FactoryBean
    -0.45
     feed
    -0.44
     Wohl
    -0.43
    POSITIVE LOGITS
     GDPR
    0.78
    Personendaten
    0.69
     iſt
    0.65
     purpoſe
    0.65
    GDPR
    0.64
     uſed
    0.62
    ſelves
    0.62
    الحياه
    0.62
     autorité
    0.62
     ErrIntOverflow
    0.61
    Activations Density 0.127%

    No Known Activations