Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 3272
    Prev
    Next
    INDEX
    Explanations

    references to scientific or legal documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Latin words or phrases

    np_acts-logits-general · gemini-2.0-flash

    latin legal and scientific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    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
    -2.60
     itſelf
    -2.56
     purpoſe
    -2.45
     pleaſure
    -2.44
     Jefus
    -2.43
     Monfieur
    -2.37
     Efq
    -2.29
     themſelves
    -2.29
     houſe
    -2.25
     raiſ
    -2.21
    POSITIVE LOGITS
     et
    0.87
     ad
    0.72
     ex
    0.60
     est
    0.60
     ab
    0.57
     non
    0.57
     f
    0.56
     pro
    0.56
     qu
    0.56
    que
    0.55
    Activations Density 0.136%

    No Known Activations