© 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. 4509
    Prev
    Next
    INDEX
    Explanations

    references to Gothic culture and dark imagery

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

    Mathematical expressions and dark themes

    np_acts-logits-general · gemini-2.0-flash

    dark and morbid themes

    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
     heureuse
    -0.57
     ArrayAdapter
    -0.56
     diligen
    -0.53
     økonom
    -0.53
    umblebee
    -0.52
     Anſ
    -0.52
     nzuri
    -0.51
    DockStyle
    -0.51
     égal
    -0.51
     bicarbon
    -0.51
    POSITIVE LOGITS
     dark
    1.40
     sinister
    1.22
    dark
    1.20
     darker
    1.18
     darkly
    1.14
     morbid
    1.14
     Dark
    1.11
     DARK
    1.11
     creepy
    1.10
     evil
    1.09
    Activations Density 0.570%

    No Known Activations