© 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 EvalsExportsinterp-engineNEWAPI 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. 12151
    Prev
    Next
    INDEX
    Explanations

    concepts related to ghosts and the afterlife

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

    ghosts or spirits

    np_acts-logits-general · gemini-2.0-flash

    ghosts and spirits

    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
    AccessorTable
    -0.86
     referenties
    -0.67
    brium
    -0.59
    enterOuterAlt
    -0.59
     становника
    -0.58
    клопе
    -0.56
    RegistryLite
    -0.56
     protoimpl
    -0.55
    setVerticalGroup
    -0.54
    entance
    -0.54
    POSITIVE LOGITS
     ghost
    1.64
     ghosts
    1.50
    ghost
    1.41
     Ghost
    1.41
    Ghost
    1.36
     ghostly
    1.36
     Ghosts
    1.31
    Ghosts
    1.18
     fantasma
    1.16
    👻
    1.14
    Activations Density 0.255%

    No Known Activations