© 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. 15-GEMMASCOPE-RES-16K
    11. 1275
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to women's reproductive health and workplace conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -1.35
     himſelf
    -1.27
     Jefus
    -1.26
     Shakspeare
    -1.25
     Monfieur
    -1.22
     itſelf
    -1.21
     Efq
    -1.19
     Chriftian
    -1.15
     Houſe
    -1.14
     themſelves
    -1.12
    POSITIVE LOGITS
     it
    0.92
     in
    0.86
     the
    0.86
     and
    0.84
     we
    0.83
     so
    0.83
     all
    0.80
     no
    0.80
     or
    0.78
     do
    0.77
    Activations Density 0.294%

    No Known Activations