© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16-GEMMASCOPE-RES-16K
    11. 13937
    Prev
    Next
    INDEX
    Explanations

    instances of pronouns and related words indicating personal connections or observations

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

    Unclosed HTML or quotation marks

    np_acts-logits-general · gemini-2.0-flash

    quote or quartile

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.78
     dan
    -0.73
     #
    -0.65
     "
    -0.64
     der
    -0.62
     regular
    -0.62
     a
    -0.59
     (
    -0.58
     bar
    -0.57
     different
    -0.57
    POSITIVE LOGITS
     متعلقه
    1.11
     مشين
    1.10
     שוליים
    1.07
     فريبيس
    0.97
     Audiodateien
    0.96
     nephe
    0.89
    Sucesor
    0.86
     referrerpolicy
    0.85
    writeFieldEnd
    0.82
    __":
    0.81
    Activations Density 0.388%

    No Known Activations