© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 14847
    Prev
    Next
    INDEX
    Explanations

    references to authors and their affiliations in academic literature

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

    Dutch surnames (van, de, der)

    np_acts-logits-general · gemini-2.0-flash

    Dutch and foreign surnames

    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
     Efq
    -0.96
     myſelf
    -0.91
     Majefty
    -0.91
     itſelf
    -0.90
     iſt
    -0.84
     pleaſure
    -0.84
     Theſe
    -0.83
     faſt
    -0.82
     themſelves
    -0.80
     Eſ
    -0.79
    POSITIVE LOGITS
     la
    0.68
     De
    0.65
    __*/
    0.62
     La
    0.58
    De
    0.54
    conia
    0.54
    AddTagHelper
    0.51
    setVerticalGroup
    0.51
    ContentAsync
    0.51
     Du
    0.51
    Activations Density 0.080%

    No Known Activations