© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 11622
    Prev
    Next
    INDEX
    Explanations

    concepts related to unity and reconciliation across divisions

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

    Text following names, titles, or locations

    np_acts-logits-general · gemini-2.0-flash

    political warnings and candidates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    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
    -1.10
     pleaſure
    -0.97
     Shakspeare
    -0.91
     purpoſe
    -0.90
     Monfieur
    -0.89
     greateſt
    -0.88
     itſelf
    -0.84
     ſmall
    -0.83
     Jefus
    -0.83
     cauſe
    -0.83
    POSITIVE LOGITS
    。「
    0.57
     «
    0.57
     “
    0.56
    ,「
    0.56
    CloseOperation
    0.52
     yesterday
    0.51
     reportedly
    0.50
    「
    0.50
     bal
    0.49
    «
    0.49
    Activations Density 0.051%

    No Known Activations