© 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. 22-GEMMASCOPE-RES-16K
    11. 13549
    Prev
    Next
    INDEX
    Explanations

    themes related to mental health and the perception of sanity

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

    insanity or irrationality

    np_acts-logits-general · gemini-2.0-flash

    expressions of craziness or insanity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     protoimpl
    -0.67
     Aquila
    -0.58
    tvguidetime
    -0.56
     duele
    -0.54
    openzeppelin
    -0.52
     elegancia
    -0.51
     bottes
    -0.51
    GENERIC
    -0.50
    Condolences
    -0.49
     pijn
    -0.49
    POSITIVE LOGITS
     crazy
    2.08
     madness
    1.94
    crazy
    1.92
     insane
    1.89
     insanity
    1.86
     Crazy
    1.82
    Crazy
    1.81
     craz
    1.74
     lunatic
    1.71
     madman
    1.65
    Activations Density 0.416%

    No Known Activations