© 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. 20-GEMMASCOPE-RES-16K
    11. 5755
    Prev
    Next
    INDEX
    Explanations

    references to themes of memory and personal reflection

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

    darkness, silence, and brokenness

    np_acts-logits-general · gemini-2.0-flash

    broken land

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Darn
    -0.81
     praticamente
    -0.73
    viamente
    -0.73
    !!!)
    -0.71
    !")
    -0.71
    Kudos
    -0.70
    iestety
    -0.69
    Yikes
    -0.69
    %!
    -0.68
    )!
    -0.68
    POSITIVE LOGITS
     fucking
    0.71
     fucked
    0.67
    fuck
    0.59
    fucking
    0.59
    genstein
    0.52
     fuck
    0.51
     maybe
    0.48
     goddamn
    0.48
     nameless
    0.47
     silent
    0.46
    Activations Density 0.635%

    No Known Activations