© 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. 2-GEMMASCOPE-RES-16K
    11. 16365
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Santa."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Steel
    -0.54
    Duff
    -0.53
    !(:
    -0.53
     https
    -0.53
    !("{
    -0.52
     inge
    -0.52
     us
    -0.52
     zw
    -0.51
     Bisch
    -0.51
    Steel
    -0.50
    POSITIVE LOGITS
     poffe
    1.15
     fevere
    1.01
     fubject
    0.96
     poffible
    0.95
     Monfieur
    0.93
     pleaſure
    0.89
     themſelves
    0.87
     houſe
    0.86
     ſever
    0.83
     fufficient
    0.82
    Activations Density 0.071%

    No Known Activations