© 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. 16-GEMMASCOPE-RES-16K
    11. 2630
    Prev
    Next
    INDEX
    Explanations

    words that signal transitions or comparisons in text

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

    after a period

    np_acts-logits-general · gemini-2.0-flash

    phrases referring to past, present, or future

    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
     Majefty
    -0.91
     Efq
    -0.90
     ―――――
    -0.86
    complexContent
    -0.85
    herself
    -0.83
     Houſe
    -0.82
     Shakspeare
    -0.81
     ་་
    -0.81
     itſelf
    -0.79
    EndContext
    -0.79
    POSITIVE LOGITS
     it
    1.26
     we
    1.25
     there
    1.07
     they
    1.03
     you
    0.97
    ,
    0.96
     I
    0.96
     this
    0.86
     the
    0.83
     he
    0.72
    Activations Density 0.397%

    No Known Activations